I
A
E
S
I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
r
t
if
ic
ia
l
I
n
t
e
ll
ig
e
n
c
e
(
I
J
-
A
I
)
V
ol
. 13, No. 4, D
e
c
e
m
be
r
2024, pp.
3761
~
3771
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v13.i4.pp
3761
-
3771
3761
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
S
yst
e
m
at
i
c
r
e
vi
e
w
o
f
ar
t
i
f
i
c
i
al
i
n
t
e
l
l
i
ge
n
c
e
w
i
t
h
n
e
ar
-
i
n
f
r
ar
e
d
i
n
b
l
u
e
b
e
r
r
i
e
s
L
is
e
t
C
ayh
u
al
la
A
m
ar
o
,
S
e
b
as
t
ia
n
R
au
R
e
ye
s
,
M
ar
ía
A
c
u
ñ
a
M
e
lé
n
d
e
z
, C
h
r
is
t
ia
n
O
val
le
D
e
pa
r
t
a
m
e
nt
o
de
I
n
ge
ni
e
r
í
a
, F
a
c
ul
t
a
d de
I
nge
ni
e
r
í
a
, U
ni
ve
r
s
i
da
d T
e
c
nol
ógi
c
a
d
e
l
P
e
r
ú,
L
i
m
a
, P
e
r
ú
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
J
a
n 9, 2024
R
e
vi
s
e
d
M
a
r
3, 2024
A
c
c
e
pt
e
d
M
a
r
21, 2024
The fruit quality has
a direct
impact on how
the fruit
looks and
how ta
sty the
fruit is.
The correct
use of
tools t
o
determine frui
t
quality
is
essential
t
o offer
the
best
product
for
the
final
consumer.
This
study
has
used
the
pr
eferred
reporting
items
for
systemati
c
reviews
and
meta
-
analyses
(PRISM
A)
methodology.
The
study
objective
was
elaborate
a
systematic
lit
erature
review
(SLR)
about
research
of
the
application
of
techniques
bas
ed
on
artificial
intell
igence
to
analyze
indicato
rs
obt
ained
by
near
i
nfr
ared
spectroscopy
(NIRS)
and
chemometrics
to
determine
the
quality
of
fruits,
including
blueberr
ies.
The
most
frequen
tly
addresse
d
indicator
is
the
s
oluble
solids
concentration
(SSC)
which
was
used
in
several
studies
with
techniques
such
as
support
vector
machines
(SVM)
and
convolutional
neural
networks
(CNN).
According
to
the
results
obtained,
it
is
possible
to
use
these
techniques
to
predict
blueberry
quality
indicators.
There
was
an
acceptable
performance
and
high
accuracy
of
these
models.
However,
futur
e
research
could
cover
other
techniques
and
help
to
provide
better
quality
control
of product
s in fo
od indu
stries.
K
e
y
w
o
r
ds
:
A
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
B
lu
e
be
r
r
ie
s
C
he
m
om
e
tr
y
F
r
ui
t
M
a
c
hi
ne
l
e
a
r
ni
ng
N
ir
s
pe
c
te
r
s
N
onde
s
tr
uc
ti
ve
e
va
lu
a
ti
on
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
C
hr
is
ti
a
n O
va
ll
e
D
e
pa
r
ta
m
e
nt
o
de
I
nge
ni
e
r
ía
, F
a
c
ul
ta
d de
I
nge
ni
e
r
ía
, U
ni
ve
r
s
id
a
d T
e
c
nol
ógi
c
a
d
e
l
P
e
r
ú
L
im
a
, P
e
r
ú
E
m
a
il
:
dova
ll
e
@
ut
p.e
du.pe
1.
I
N
T
R
O
D
U
C
T
I
O
N
B
lu
e
be
r
r
ie
s
a
r
e
f
ood
w
it
h
hi
gh
nut
r
it
io
na
l
va
lu
e
,
a
nd
th
e
y
ha
ve
be
ne
f
it
s
r
e
la
te
d
to
he
a
lt
h
to
im
pa
c
t
on
qua
li
ty
of
pe
opl
e
´
s
l
iv
e
s
.
B
lu
e
be
r
r
ie
s
a
ls
o
a
r
e
ta
s
ty
f
or
m
o
s
t
pe
opl
e
.
T
he
y
ha
ve
c
ul
ti
va
ti
on
qua
li
ti
e
s
th
a
t
a
r
e
us
e
f
ul
f
or
r
a
pi
dl
y
gr
ow
in
g
a
nd
th
a
t'
s
w
hy
th
e
ir
popula
r
it
y
ha
s
be
e
n
s
pr
e
a
di
ng
a
r
ound
th
e
w
or
ld
[
1]
.
A
s
bl
ue
be
r
r
ie
s
be
c
a
m
e
popula
r
,
pe
opl
e
a
l
s
o
de
m
a
nde
d
a
n
a
c
c
e
pt
a
bl
e
qua
li
ty
f
or
it
.
B
lu
e
be
r
r
y
p
r
oduc
ti
on
is
a
ls
o
in
c
r
e
a
s
in
g ye
a
r
a
f
te
r
ye
a
r
, s
o t
he
s
ta
nda
r
d f
or
pi
c
ki
ng i
s
t
he
f
r
ui
t
in
a
s
pe
c
if
ie
d m
a
tu
r
it
y t
im
e
[
2]
.
B
lu
e
be
r
r
ie
s
'
r
ip
e
ne
s
s
a
f
f
e
c
ts
how
th
e
y
ta
s
te
a
nd
how
lo
ng
th
e
y
c
a
n
be
s
to
r
e
d
w
it
hout
ge
tt
in
g
r
ot
.
S
om
e
qua
li
ty
te
s
ti
ng
c
om
bi
ne
s
r
ip
e
ni
ng
pa
r
a
m
e
te
r
s
a
nd
ot
he
r
c
ha
r
a
c
te
r
is
ti
c
s
b
a
s
e
d
on
pr
e
-
ha
r
ve
s
t
f
a
c
to
r
s
.
I
n
a
c
om
m
on
pr
oc
e
s
s
,
th
e
bl
ue
be
r
r
y
qua
li
ty
te
s
t
c
a
n
e
va
lu
a
te
s
om
e
ke
y
c
ha
r
a
c
te
r
is
ti
c
s
li
ke
s
ol
ubl
e
s
ol
id
s
c
onc
e
nt
r
a
ti
on
(
S
S
C
)
to
de
te
r
m
in
e
a
c
or
r
e
c
t
ha
r
ve
s
t
m
a
tu
r
it
y
ti
m
e
,
how
e
ve
r
th
is
is
done
de
s
tr
uc
ti
ve
ly
b
y
di
s
c
a
r
di
ng
s
e
ve
r
a
l
bl
ue
be
r
r
y
s
a
m
pl
e
s
[
3]
.
S
uga
r
is
th
e
m
a
in
c
om
pone
nt
of
f
r
ui
t
qua
li
ty
a
nd
f
la
vor
.
I
t
a
ls
o
a
f
f
e
c
ts
t
he
a
r
om
a
ti
c
c
om
pounds
a
nd
c
ol
or
pi
gm
e
nt
s
of
bl
ue
be
r
r
ie
s
[
4]
.
T
hi
s
s
tu
dy i
nve
s
ti
ga
te
d how ne
a
r
in
f
r
a
r
e
d s
pe
c
tr
os
c
opy (
N
I
R
S
)
w
it
h ot
he
r
t
e
c
hnol
ogi
e
s
l
ik
e
m
a
c
hi
ne
le
a
r
ni
ng a
nd t
e
c
hni
que
s
l
ik
e
c
he
m
om
e
tr
ic
s
c
oul
d be
us
e
d t
o i
m
pr
ove
qua
li
ty
e
va
lu
a
ti
on of
bl
ue
be
r
r
y
f
r
ui
t
i
n
a
na
ti
ona
l
c
ont
e
xt
.
N
I
R
S
ha
s
be
e
n
m
os
tl
y
in
te
nd
e
d
f
or
us
e
in
th
e
a
gr
i
-
f
ood
in
dus
tr
y
a
nd
it
i
s
e
m
pl
oye
d
a
t
di
f
f
e
r
e
nt
s
ta
ge
s
of
a
gr
ow
e
r
'
s
s
uppl
y
c
ha
in
[
5]
.
N
I
R
S
ha
s
be
e
n us
e
d
a
s
a
r
a
pi
d,
non
-
de
s
tr
uc
ti
ve
s
c
r
e
e
ni
ng
to
ol
to
de
te
r
m
in
e
c
e
r
ta
in
f
r
ui
t
a
tt
r
ib
ut
e
s
f
or
pos
th
a
r
ve
s
t
qua
li
ty
e
va
lu
a
ti
on
[
6]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
. 13, No. 4, D
e
c
e
m
be
r
2024:
3761
-
3771
3762
I
n
c
om
bi
na
ti
on
w
it
h
c
he
m
om
e
tr
ic
s
te
c
hni
que
s
,
it
h
a
s
s
how
n
gr
e
a
t
pot
e
nt
ia
l
f
or
th
e
de
te
r
m
in
a
ti
on
of
phys
ic
a
l
a
nd
c
h
e
m
ic
a
l
pa
r
a
m
e
te
r
s
s
uc
h
a
s
to
ta
l
s
ol
ubl
e
s
ol
id
s
(
T
S
S
)
a
nd
to
ta
l
ti
tr
a
ta
bl
e
a
c
id
it
y
(
T
A
)
.
T
hi
s
te
c
hni
que
a
ll
ow
s
f
or
de
te
r
m
in
in
g
phys
ic
oc
he
m
ic
a
l
pr
ope
r
ti
e
s
r
e
la
te
d
to
va
r
io
us
bi
oc
he
m
ic
a
l
c
ha
nge
s
s
u
c
h
a
s
f
r
ui
t
r
ip
e
ni
ng.
F
ur
th
e
r
m
or
e
,
la
r
ge
a
m
ount
s
o
f
da
ta
m
a
y
be
a
va
il
a
bl
e
th
a
t
r
e
qui
r
e
m
ul
ti
va
r
ia
te
s
ta
ti
s
ti
c
a
l
a
ppr
oa
c
he
s
to
id
e
nt
if
y
th
e
m
os
t
r
e
l
e
va
nt
in
f
or
m
a
ti
on
f
r
om
la
r
ge
da
ta
s
e
t
s
a
nd
c
r
e
a
te
pr
e
di
c
ti
on
a
nd
c
la
s
s
if
ic
a
ti
on mode
ls
w
it
h pr
a
c
ti
c
a
l
a
ppl
ic
a
ti
ons
[
4]
.
I
n
s
om
e
r
e
s
e
a
r
c
h,
w
e
f
ound
us
e
s
of
N
I
R
S
in
c
om
bi
na
ti
on
w
it
h
c
he
m
om
e
tr
ic
s
f
or
th
e
e
va
lu
a
ti
on
of
S
S
C
in
di
f
f
e
r
e
nt
f
r
ui
ts
to
opt
im
iz
e
th
e
ti
m
e
of
qua
li
ty
e
va
lu
a
t
io
n
a
nd
in
c
r
e
a
s
e
it
s
e
f
f
ic
ie
nc
y.
A
c
c
or
di
ng
to
C
e
r
e
z
o
e
t
al
.
[
7]
, N
I
R
S
a
nd pr
in
c
ip
a
l
c
om
pone
nt
a
na
ly
s
is
(
P
C
A
)
a
r
e
us
e
d t
o de
te
r
m
in
e
th
e
qua
li
ty
of
ol
iv
e
oi
l
ba
s
e
d
on
th
e
S
S
C
,
w
hi
c
h
d
e
te
r
m
in
e
s
a
hi
ghe
r
va
lu
e
f
or
t
he
pr
e
di
c
ti
on
a
nd
c
la
s
s
if
ic
a
ti
on
of
m
a
tu
r
it
y.
A
c
c
or
di
ng
to
S
a
nt
os
e
t
al
.
[
8]
,
it
e
xpl
or
e
d
th
e
u
s
e
of
N
I
R
S
a
nd
pa
r
ti
a
l
le
a
s
t
s
qua
r
e
s
r
e
gr
e
s
s
io
n
(
P
L
S
R
)
to
e
va
lu
a
te
th
e
m
a
tu
r
it
y
of
c
it
r
us
f
r
ui
ts
.
I
t
a
ls
o
us
e
d
pr
e
pr
oc
e
s
s
in
g
te
c
hni
que
s
s
uc
h
a
s
m
ul
ti
pl
ic
a
ti
ve
s
c
a
tt
e
r
c
or
r
e
c
ti
on
(
M
S
C
)
a
nd
s
ta
nda
r
d
nor
m
a
l
va
r
ia
te
(
S
N
V
)
th
a
t
a
c
hi
e
ve
d
be
tt
e
r
pr
e
c
is
io
n
of
th
e
S
S
C
s
of
th
e
f
r
ui
ts
.
M
ont
e
c
c
hi
a
r
in
i
e
t
al
.
[
9]
pr
opos
e
d m
a
c
hi
ne
l
e
a
r
ni
ng mode
ls
s
u
c
h a
s
c
onvolut
io
na
l
ne
ur
a
l
ne
twor
k (
C
N
N
)
a
nd
f
e
e
df
or
w
a
r
d
ne
ur
a
l
ne
twor
k
(
F
N
N
)
in
c
om
bi
na
ti
on
w
it
h
N
I
R
S
a
nd
P
C
A
f
or
th
e
e
va
lu
a
ti
on
of
S
S
C
in
O
'
N
e
a
l
a
nd
E
m
e
r
a
ld
va
r
ie
ty
bl
ue
be
r
r
ie
s
w
it
h
a
n
a
c
c
ur
a
c
y
of
98%
.
A
c
c
or
di
ng
to
R
ungpic
ha
ya
pi
c
he
t
e
t
al
.
[
10]
,
it
us
e
d
pa
r
ti
a
l
le
a
s
t
s
qua
r
e
s
(
P
L
S
)
r
e
gr
e
s
s
io
n a
s
a
pr
e
di
c
ti
on mod
e
l
f
or
m
a
ngo S
S
C
w
it
h
a
pr
e
c
is
io
n of
87%
,
t
he
r
e
s
ul
t
w
a
s
ve
r
y
lo
w
due
to
th
e
ti
m
e
in
w
hi
c
h
th
e
ha
r
ve
s
ts
w
e
r
e
c
a
r
r
ie
d
out
,
w
hi
c
h
de
te
r
m
in
e
d
a
r
e
la
ti
ons
hi
p
th
a
t
w
a
s
not
s
o
a
ppr
opr
ia
te
.
F
or
pr
e
di
c
ti
ons
,
F
e
r
r
a
r
a
e
t
al
.
[
11]
de
ve
lo
pe
d
pr
e
di
c
ti
ve
m
ode
l
s
f
or
th
e
e
va
lu
a
ti
on
of
th
e
qua
li
ty
of
th
e
gr
a
pe
s
lo
c
a
te
d
in
th
e
vi
ne
ya
r
ds
,
w
hi
c
h
de
te
r
m
in
e
s
th
e
e
xa
c
t
ti
m
e
th
a
t
s
houl
d
be
ha
r
ve
s
te
d,
ho
w
e
ve
r
,
s
om
e
li
m
it
a
ti
ons
w
e
r
e
f
ound
f
or
c
ol
le
c
t
in
g
da
ta
di
r
e
c
tl
y
in
th
e
vi
ne
y
a
r
ds
,
s
u
c
h
a
s
th
e
s
ha
de
th
a
t
di
s
pe
r
s
e
th
e
d
a
ta
.
D
it
c
ha
r
oe
n
e
t
al
.
[
12]
pr
opos
e
s
m
ode
ls
s
u
c
h
a
s
s
uppor
t
v
e
c
to
r
m
a
c
hi
ne
(
S
V
M
)
a
nd
k
-
ne
a
r
e
s
t
ne
ig
hbor
s
(
K
N
N
)
f
or
th
e
pr
e
di
c
ti
on
of
S
S
C
s
of
dur
ia
n
f
r
ui
t,
di
f
f
e
r
e
nt
te
c
hni
que
s
s
uc
h
a
s
M
S
C
a
nd
S
N
V
w
e
r
e
us
e
d
to
c
a
li
br
a
te
th
e
s
pe
c
tr
a
l
da
ta
,
w
hi
c
h
he
l
ps
to
im
pr
ove
m
ode
l
tr
a
in
in
g
w
hi
c
h
ha
d
a
n
a
ppr
oxi
m
a
te
a
c
c
ur
a
c
y
of
89%
.
H
ow
e
v
e
r
,
it
is
r
e
c
om
m
e
nd
e
d
to
ha
ve
m
or
e
te
s
t
da
ta
to
im
pr
ove
th
e
pe
r
f
or
m
a
nc
e
of
t
he
m
ode
ls
.
I
n
s
um
m
a
r
y,
our
in
ve
s
ti
ga
ti
on
s
ugge
s
ts
th
a
t
a
w
e
ll
-
pe
r
f
or
m
in
g
bl
ue
be
r
r
y
S
S
C
de
te
c
ti
on
m
ode
l
c
a
n
he
lp
f
a
r
m
e
r
s
a
nd
la
bor
a
to
r
ie
s
to
qui
c
kl
y
de
te
c
t
th
e
r
ip
e
ne
s
s
of
bl
ue
be
r
r
ie
s
m
or
e
a
c
c
ur
a
te
ly
.
T
hi
s
a
ll
ow
s
th
e
m
to
id
e
nt
if
y
th
e
opt
im
a
l
bl
ue
be
r
r
y
ha
r
ve
s
t
ti
m
e
a
nd
r
e
duc
e
th
e
c
ur
r
e
nt
qua
li
ty
e
va
lu
a
ti
on
th
a
t
r
e
qui
r
e
s
a
lo
t
of
ti
m
e
a
nd
m
a
npowe
r
.
T
h
a
t
is
w
hy
in
th
e
pr
e
s
e
nt
r
e
vi
e
w
,
w
e
e
xp
lo
r
e
d
di
f
f
e
r
e
nt
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
m
ode
ls
in
c
om
bi
na
ti
on
w
it
h
N
I
R
S
a
nd
c
he
m
om
e
tr
ic
te
c
hni
que
s
f
or
S
S
C
de
te
c
ti
on.
L
ik
e
w
is
e
,
va
r
io
us
r
e
s
e
a
r
c
h
w
il
l
he
lp
to
de
e
pe
n t
he
r
e
la
ti
ons
hi
p be
twe
e
n bl
ue
be
r
r
y s
uga
r
c
ont
e
nt
a
nd
it
s
r
ip
e
ne
s
s
t
o f
a
c
il
it
a
te
t
hi
s
d
e
te
c
ti
on.
2.
M
E
T
H
O
D
2.1. S
ys
t
e
m
at
ic
s
e
a
r
c
h
s
t
r
at
e
gy
I
n
th
is
r
e
s
e
a
r
c
h
th
e
P
I
C
O
m
e
th
od
w
a
s
u
s
e
d.
I
ts
n
a
m
e
is
th
e
i
ni
ti
a
ls
of
th
e
w
or
ds
P
(
popula
ti
on)
,
I
(
in
te
r
ve
nt
io
n)
,
C
(
c
om
pa
r
is
on)
,
a
nd
O
(
out
c
om
e
)
.
T
hi
s
m
e
th
od
a
ll
ow
s
th
e
f
or
m
ul
a
ti
on
of
s
tr
a
te
gi
c
que
s
ti
ons
to
c
a
r
r
y
out
m
or
e
pr
e
c
is
e
a
nd
e
f
f
e
c
ti
ve
s
e
a
r
c
he
s
f
or
a
r
ti
c
le
s
[
13]
.
I
n
a
ddi
ti
on,
th
e
f
o
r
m
ul
a
ti
on
of
th
e
P
I
C
O
que
s
ti
on a
nd i
ts
c
om
pone
nt
s
t
ha
t
he
lp
e
d t
o f
or
m
ul
a
te
t
he
r
e
s
e
a
r
c
h que
s
ti
on w
a
s
c
a
r
r
ie
d out a
nd c
a
n be
s
e
e
n i
n
T
a
bl
e
1.
A
ddi
ti
ona
ll
y,
a
di
s
a
ggr
e
ga
te
d
P
I
C
O
ta
bl
e
w
a
s
m
a
de
w
he
r
e
th
e
ke
yw
or
d
s
in
e
a
c
h
c
om
pon
e
nt
w
e
r
e
id
e
nt
if
ie
d a
nd t
hus
ge
ne
r
a
te
t
he
s
e
a
r
c
h e
qua
ti
on t
ha
t
w
il
l
he
lp
t
o obta
in
m
or
e
a
c
c
ur
a
te
r
e
s
ul
ts
;
th
is
c
a
n be
s
e
e
n
in
T
a
bl
e
2.
2.2. S
e
ar
c
h
e
q
u
at
io
n
N
e
xt
,
s
e
a
r
c
he
s
w
e
r
e
pe
r
f
or
m
e
d
in
two
da
ta
ba
s
e
s
f
oc
us
e
d
on
r
e
s
e
a
r
c
h,
w
hi
c
h
a
r
e
S
c
opus
a
nd
P
ubM
e
d,
w
he
r
e
th
e
e
qu
a
ti
on
w
a
s
f
or
m
ul
a
te
d
ba
s
e
d
on
th
e
ke
y
w
or
ds
de
f
in
e
d
in
T
a
bl
e
2.
A
ddi
ti
ona
ll
y,
ot
he
r
f
il
te
r
s
w
e
r
e
a
dde
d,
s
u
c
h
a
s
th
a
t
th
e
publ
ic
a
ti
ons
s
houl
d
be
be
t
w
e
e
n
2019
a
nd
2023
a
nd
th
a
t
th
e
doc
um
e
nt
s
s
houl
d
be
s
ys
te
m
a
ti
c
r
e
vi
e
w
s
a
nd
a
r
ti
c
le
s
.
A
s
a
r
e
s
ul
t,
a
to
ta
l
of
265
in
ve
s
ti
ga
ti
ons
w
e
r
e
obt
a
in
e
d
f
o
r
S
c
opus
a
nd a
t
ot
a
l
of
8 i
nve
s
ti
ga
ti
ons
w
e
r
e
obt
a
in
e
d f
r
om
P
ubM
e
d.
T
he
f
ol
lo
w
in
g i
s
de
s
c
r
ib
e
d i
n T
a
bl
e
3.
T
a
bl
e
1. P
I
C
O
que
s
ti
on
a
nd i
ts
c
om
pone
nt
s
Q
ue
s
t
i
on
P
ICO
Com
pone
nt
s
‒
RQ
:
H
ow
w
oul
d
t
he
us
e
of
a
m
a
c
hi
ne
l
e
a
rn
i
ng
m
ode
l
ba
s
e
d
on
N
IRS
a
nd
c
he
m
om
e
t
ri
c
s
i
m
prove
t
he
e
v
a
l
ua
t
i
on
of
t
he
i
n
t
e
rna
l
qua
l
i
t
y
of
bl
ue
be
rri
e
s
c
o
m
pa
re
d
t
o
t
ra
di
t
i
ona
l
de
s
t
ruc
t
i
v
e
e
va
l
ua
t
i
on?
‒
RQ
1:
W
ha
t
ki
nd
of
bl
ue
be
rry
qua
l
i
t
y
i
nd
i
c
a
t
ors
ha
ve
be
e
n
pre
di
c
t
e
d
us
i
ng
m
a
c
hi
n
e
l
e
a
rni
ng
m
e
t
hods
?
‒
RQ
2:
W
ha
t
a
re
t
he
d
i
ffe
re
n
t
m
a
c
h
i
ne
l
e
a
rni
ng
t
e
c
hni
que
s
t
ha
t
ha
ve
be
e
n
a
ppl
i
e
d
t
o
pre
di
c
t
bl
ue
b
e
rry
qua
l
i
t
y?
‒
RQ
3:
W
ha
t
a
re
t
he
c
he
m
o
m
e
t
r
i
c
t
e
c
hn
i
que
s
us
e
d
i
n
bl
ue
be
rry
qua
l
i
t
y
pre
di
c
t
i
on?
‒
RQ
4:
H
ow
ha
ve
you
c
a
rri
e
d
out
t
he
pe
rform
a
nc
e
m
e
t
ri
c
s
of
m
a
c
hi
n
e
l
e
a
rn
i
ng
m
ode
l
s
t
o
pre
di
c
t
t
he
i
n
t
e
rna
l
qua
l
i
t
y
of
bl
ue
be
rr
i
e
s
?
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
Sy
s
te
m
at
ic
r
e
v
ie
w
of
a
r
ti
fi
c
ia
l
in
te
ll
ig
e
nc
e
w
it
h ne
ar
-
in
fr
a
r
e
d i
n
bl
ue
be
r
r
ie
s
…
(
L
is
e
t
C
a
y
hual
la
A
m
ar
o
)
3763
T
a
bl
e
2. D
is
a
ggr
e
ga
te
d P
I
C
O
t
a
bl
e
K
e
yw
or
d
E
qua
t
i
on s
ynt
a
x
P
:
P
r
obl
e
m
/
P
opul
a
t
i
on
B
l
ue
be
r
r
i
e
s
f
or
qua
l
i
t
y
e
va
l
ua
t
i
on
P
os
t
ha
r
ve
s
t
, f
r
ui
t
s
, be
r
r
i
e
s
P
os
t
ha
r
ve
s
t
O
R
f
r
ui
t
s
O
R
be
r
r
i
e
s
I
:
I
nt
e
r
ve
nt
i
on
M
a
c
hi
ne
l
e
a
r
ni
ng m
ode
l
ba
s
e
d on N
I
R
S
a
nd
c
he
m
om
e
t
r
i
c
s
M
a
c
hi
ne
l
e
a
r
ni
ng,
N
I
R
,
n
e
a
r
i
nf
r
a
r
e
d s
pe
c
t
r
os
c
opy,
c
he
m
om
e
t
r
y, a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
nc
e
"ma
c
hi
ne
l
e
a
r
ni
ng" O
R
"nir
" O
R
"ne
a
r
i
nf
r
a
r
e
d s
pe
c
t
r
os
c
opy" O
R
"c
he
m
om
e
t
r
y"
O
R
"a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
nc
e
".
C
:
C
om
pa
r
i
s
on
T
r
a
di
t
i
ona
l
de
s
t
r
uc
t
i
ve
e
va
l
ua
t
i
on
M
a
t
ur
i
t
y
, s
ol
ubl
e
s
ol
i
ds
,
t
i
t
r
a
t
a
bl
e
a
c
i
di
t
y, de
s
t
r
uc
t
i
ve
m
e
t
hod, t
r
a
di
t
i
ona
l
".
m
a
t
ur
i
t
y O
R
"s
ol
ubl
e
s
ol
i
ds
" O
R
"ti
t
r
a
t
a
bl
e
a
c
i
di
t
y" O
R
"de
s
t
r
uc
t
i
ve
m
e
t
hod" O
R
"tr
a
di
t
i
ona
l
".
O
:
R
e
s
ul
t
s
I
m
pr
ove
d i
nt
e
r
na
l
qua
l
i
t
y a
s
s
e
s
s
m
e
nt
Q
ua
l
i
t
y
e
va
l
ua
t
i
on, r
e
s
ul
t
s
,
non
-
de
s
t
r
uc
t
i
ve
, e
va
l
ua
t
i
on,
e
va
l
ua
t
i
on
"qua
l
i
t
y e
va
l
ua
t
i
on" O
R
"r
e
s
ul
t
s
"
O
R
"non
-
de
s
t
r
uc
t
i
ve
" O
R
"e
va
l
ua
t
i
on".
T
a
bl
e
3. D
a
ta
b
a
s
e
s
e
a
r
c
h
D
a
t
a
ba
s
e
E
qua
t
i
on
R
e
s
ul
t
s
obt
a
i
ne
d
S
C
O
P
U
S
T
I
T
L
E
-
A
B
S
-
K
E
Y
(
pos
t
ha
r
ve
s
t
O
R
f
r
ui
t
s
O
R
be
r
r
i
e
s
A
N
D
"ma
c
hi
ne
l
e
a
r
ni
ng"
O
R
"nir
" O
R
"
ne
a
r
i
nf
r
a
r
e
d s
pe
c
t
r
os
c
opy" O
R
"c
he
m
om
e
t
r
y" O
R
"a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
nc
e
" A
N
D
m
a
t
ur
i
t
y O
R
"s
ol
ubl
e
s
ol
i
ds
" O
R
"ti
t
r
a
t
a
bl
e
a
c
i
di
t
y" O
R
" de
s
t
r
uc
t
i
ve
m
e
t
hod" O
R
" tr
a
di
t
i
o
na
l
" A
N
D
"qua
l
i
t
y e
va
l
ua
t
i
on" O
R
"r
e
s
ul
t
s
"
O
R
"non
-
de
s
t
r
uc
t
i
ve
" O
R
"e
va
l
ua
t
i
on")
A
N
D
P
U
B
Y
E
A
R
>
2018 A
N
D
P
U
B
Y
E
A
R
< 2025 A
N
D
(
L
I
M
I
T
-
T
O
(
D
O
C
T
Y
P
E
, "a
r
")
O
R
L
I
M
I
T
-
T
O
(
D
O
C
T
Y
P
E
, "r
e
")
)
A
N
D
(
L
I
M
I
T
-
T
O
(
O
A
, "a
l
l
")
)
265
P
U
B
M
E
D
(
pos
t
ha
r
ve
s
t
O
R
f
r
ui
t
s
O
R
be
r
r
i
e
s
)
A
N
D
(
"ma
c
hi
ne
l
e
a
r
ni
ng" O
R
"nir
" O
R
"
ne
a
r
i
nf
r
a
r
e
d
s
pe
c
t
r
os
c
opy" O
R
"c
he
m
om
e
t
r
y" O
R
"a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
nc
e
")
A
N
D
(
m
a
t
ur
i
t
y O
R
"s
ol
ubl
e
s
ol
i
ds
" O
R
"ti
t
r
a
t
a
bl
e
a
c
i
di
t
y" O
R
" de
s
t
r
uc
t
i
ve
m
e
t
hod" O
R
" tr
a
di
t
i
ona
l
")
A
N
D
(
"qua
l
i
t
y
e
va
l
ua
t
i
on" O
R
"r
e
s
ul
t
s
"
O
R
"non
-
de
s
t
r
uc
t
i
ve
" O
R
"e
va
l
ua
t
i
on")
8
2.3. I
n
c
lu
s
io
n
an
d
e
xc
lu
s
io
n
c
r
it
e
r
ia
I
nc
lu
s
io
n
a
nd
e
xc
lu
s
io
n
c
r
it
e
r
ia
w
e
r
e
th
e
n
de
ve
lo
pe
d
ba
s
e
d
o
n
th
e
a
r
ti
c
le
s
f
ound
in
th
e
da
ta
ba
s
e
s
.
I
m
por
ta
nt
to
pi
c
s
th
a
t
s
houl
d
be
in
c
lu
de
d
in
th
e
pa
pe
r
s
w
e
r
e
id
e
nt
if
ie
d
to
he
lp
m
a
ke
a
be
tt
e
r
s
e
le
c
ti
on
f
or
th
e
r
e
s
e
a
r
c
h
. T
h
e
c
r
it
e
r
ia
a
r
e
de
f
in
e
d i
n T
a
bl
e
4
.
T
a
bl
e
4. I
nc
lu
s
io
n a
nd
e
xc
lu
s
io
n c
r
it
e
r
ia
I
nc
l
us
i
on
c
r
i
t
e
r
i
a
E
xc
l
us
i
on
c
r
i
t
e
r
i
a
C
I
1:
S
t
udi
e
s
s
houl
d i
nc
l
ude
pr
e
di
c
t
i
ve
m
ode
l
s
of
qua
l
i
t
y
pa
r
a
m
e
t
e
r
s
.
C
I
2:
S
t
udi
e
s
s
houl
d i
nc
l
ude
t
he
i
m
pl
e
m
e
nt
a
t
i
on of
c
he
m
om
e
t
r
i
c
s
a
nd m
a
c
hi
ne
l
e
a
r
ni
ng.
C
I
3:
S
t
udi
e
s
s
houl
d i
nc
l
ude
t
he
us
e
of
N
i
r
s
pe
c
t
r
a
i
n f
r
ui
t
s
.
C
I
4:
S
t
udi
e
s
s
houl
d i
nc
l
ude
m
a
c
hi
ne
l
e
a
r
ni
ng or
de
e
p l
e
a
r
n
i
ng
a
ppr
oa
c
he
s
t
o c
l
a
s
s
i
f
y a
f
r
ui
t
.
C
I
5:
S
t
udi
e
s
s
houl
d i
nc
l
ude
m
e
t
hods
f
or
i
nf
or
m
a
t
i
on
e
xt
r
a
c
t
i
on t
o t
r
a
i
n
m
a
c
hi
ne
l
e
a
r
ni
ng
m
ode
l
s
.
C
I
6:
S
t
udi
e
s
s
houl
d i
nc
l
ude
c
he
m
om
e
t
r
i
c
t
e
c
hni
que
s
.
C
E
1:
D
oc
um
e
nt
s
t
ha
t
do not
us
e
N
I
R
S
f
or
i
nf
or
m
a
t
i
on c
a
pt
ur
e
.
C
E
2:
D
oc
um
e
nt
s
t
ha
t
do not
i
m
pl
e
m
e
nt
c
he
m
om
e
t
r
i
c
s
.
C
E
3:
P
a
pe
r
s
t
ha
t
do not
m
e
nt
i
on
m
a
c
hi
ne
l
e
a
r
ni
ng
t
e
c
hni
que
s
.
S
C
4:
T
he
doc
um
e
nt
s
t
ha
t
do not
s
pe
a
k of
t
he
qua
l
i
t
y of
t
he
f
r
ui
t
s
.
C
E
5:
S
t
udi
e
s
t
ha
t
do not
de
a
l
w
i
t
h
m
a
c
hi
ne
l
e
a
r
ni
ng
or
a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
nc
e
or
de
e
p l
e
a
r
ni
ng
.
C
E
6:
D
oc
um
e
nt
s
t
ha
t
a
r
e
pr
i
or
t
o 2019.
C
E
7:
P
ubl
i
c
a
t
i
ons
t
ha
t
a
r
e
di
f
f
e
r
e
nt
f
r
o
m
E
ngl
i
s
h or
S
pa
ni
s
h.
2.4. S
e
le
c
t
io
n
p
r
oc
e
s
s
F
or
th
e
s
e
le
c
ti
on
of
a
r
ti
c
le
s
,
th
e
P
R
I
S
M
A
f
lo
w
c
ha
r
t
w
a
s
u
s
e
d
to
he
lp
id
e
nt
if
y
r
e
s
e
a
r
c
h
a
r
ti
c
le
s
th
a
t
be
s
t
f
it
th
e
to
pi
c
of
s
ys
te
m
a
ti
c
r
e
vi
e
w
s
by
f
il
te
r
in
g
by
e
xc
lu
s
io
n
a
nd
in
c
lu
s
io
n
c
r
it
e
r
ia
[
14]
.
T
he
f
ir
s
t
s
te
p
w
a
s
e
li
m
in
a
ti
ng
dupl
ic
a
te
a
r
ti
c
le
s
,
th
e
n
va
li
da
ti
ng
c
om
pl
ia
nc
e
w
it
h
th
e
in
c
lu
s
io
n
a
nd
e
xc
lu
s
io
n
c
r
it
e
r
ia
,
a
nd
f
in
a
ll
y
obt
a
in
in
g
th
e
a
r
ti
c
le
s
r
e
le
va
nt
to
th
e
r
e
s
e
a
r
c
h.
N
e
xt
in
F
ig
ur
e
1,
a
r
e
vi
e
w
of
273
doc
um
e
nt
s
s
e
le
c
te
d
f
r
om
th
e
s
e
a
r
c
h
in
th
e
da
ta
b
a
s
e
s
w
a
s
c
a
r
r
ie
d
out
,
w
he
r
e
265
doc
um
e
nt
s
w
e
r
e
s
e
le
c
te
d
f
r
om
S
c
opus
a
nd
8
doc
um
e
nt
s
f
r
om
P
ubM
e
d. O
f
t
he
t
ot
a
l
num
be
r
of
a
r
ti
c
le
s
, t
he
r
e
vi
e
w
of
t
he
a
bs
tr
a
c
t
a
s
w
e
ll
a
s
t
he
t
it
le
of
e
a
c
h
a
r
ti
c
le
w
a
s
c
a
r
r
ie
d
out
a
nd
a
to
ta
l
of
130
w
e
r
e
e
li
m
in
a
te
d
f
or
not
in
c
lu
di
ng
th
e
to
pi
c
s
of
N
I
R
S
a
nd
c
he
m
om
e
tr
ic
s
,
in
a
ddi
ti
on
to
not
in
c
lu
di
ng
m
e
nt
io
n
of
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
to
pi
c
s
s
u
c
h
a
s
pr
e
di
c
ti
ve
m
od
e
ls
,
m
a
c
hi
ne
le
a
r
ni
ng
or
de
e
p
le
a
r
ni
ng.
143
do
c
um
e
nt
s
r
e
m
a
in
e
d
w
it
h
th
e
de
f
in
e
d
to
pi
c
s
.
T
h
e
n
8
a
r
ti
c
le
s
ha
ve
be
e
n
e
li
m
in
a
te
d
be
c
a
us
e
th
e
y
a
r
e
not
f
ul
ly
a
va
il
a
bl
e
f
or
a
c
o
m
pl
e
te
r
e
vi
e
w
.
A
f
te
r
r
e
vi
e
w
in
g
th
e
r
e
m
a
in
in
g
135
a
r
ti
c
le
s
,
90
a
r
ti
c
le
s
ha
v
e
be
e
n
e
x
c
lu
de
d
f
or
f
oc
us
in
g
onl
y
on
s
pe
c
tr
a
l
im
a
gi
ng
a
nd
por
ta
bl
e
da
ta
a
c
qui
s
it
io
n
de
vi
c
e
s
;
1
a
r
ti
c
le
f
or
a
ddr
e
s
s
in
g
th
e
u
s
e
of
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
a
s
th
e
m
a
in
to
pi
c
;
3
a
r
ti
c
le
s
f
or
f
oc
us
in
g
on
F
T
-
N
I
R
a
nd
1
a
r
ti
c
le
f
or
a
ddr
e
s
s
in
g
th
e
u
s
e
of
n
it
r
oge
n
is
ot
ope
r
a
di
a
ti
on
.
40
a
r
ti
c
le
s
m
e
t
th
e
c
r
it
e
r
ia
f
or
i
nc
lu
s
io
n. T
he
P
R
I
S
M
A
f
lo
w
c
ha
r
t
pr
e
pa
r
e
d f
or
t
he
r
e
s
e
a
r
c
h i
s
s
how
n
in
F
ig
ur
e
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
. 13, No. 4, D
e
c
e
m
be
r
2024:
3761
-
3771
3764
F
ig
ur
e
1. P
R
I
S
M
A
f
lo
w
di
a
gr
a
m
3.
R
E
S
U
L
T
S
A
N
D
D
I
S
C
U
S
S
I
O
N
3.1.
B
ib
li
om
e
t
r
ic
an
al
ys
is
B
ib
li
om
e
tr
ic
a
na
ly
s
is
is
v
e
r
y
va
lu
a
bl
e
s
in
c
e
it
f
a
c
il
it
a
te
s
th
e
in
te
r
pr
e
ta
ti
on
of
la
r
ge
a
m
ount
s
of
da
ta
a
nd
pr
ovi
de
s
a
c
le
a
r
e
r
in
s
ig
ht
in
to
nove
l
id
e
a
s
f
or
r
e
s
e
a
r
c
h
[
15]
.
A
f
te
r
th
e
a
ppl
ic
a
ti
on
of
th
e
doc
um
e
nt
s
e
le
c
ti
on
pr
oc
e
s
s
,
40
s
tu
di
e
s
w
e
r
e
obt
a
in
e
d
f
or
th
e
s
ys
te
m
a
ti
c
r
e
vi
e
w
.
F
or
th
e
e
la
bor
a
ti
on
of
F
ig
ur
e
2,
th
e
s
ys
te
m
a
ti
c
r
e
vi
e
w
m
a
in
te
r
m
s
w
e
r
e
"
ne
a
r
in
f
r
a
r
e
d
s
pe
c
tr
os
c
opy
"
,
"
a
na
ly
s
is
"
,
"
f
r
ui
ts
"
,
a
nd
"
m
a
c
hi
ne
le
a
r
ni
ng"
in
c
lu
de
d
in
th
e
ti
tl
e
s
,
ke
y
w
or
ds
or
a
b
s
tr
a
c
ts
of
th
e
s
e
pa
p
e
r
s
.
S
pe
c
ia
li
z
e
d
da
ta
a
na
ly
s
is
s
of
twa
r
e
known
a
s
V
O
S
vi
e
w
e
r
w
a
s
us
e
d a
nd a
c
c
or
di
ng t
o
R
odr
ig
ue
z
e
t
al
.
[
16
]
it
s
e
r
ve
s
t
o buil
d bi
bl
io
m
e
tr
ic
ne
twor
ks
ba
s
e
d on
da
ta
dow
nl
oa
de
d f
r
om
bi
bl
io
gr
a
phi
c
da
ta
ba
s
e
s
a
nd t
hus
de
te
r
m
in
e
t
he
r
e
le
va
nc
e
a
nd r
e
la
ti
ons
hi
p be
twe
e
n t
he
ke
y c
om
pone
nt
s
of
t
he
r
e
vi
e
w
.
F
ig
ur
e
2. A
na
ly
s
is
of
c
onne
c
ti
ons
be
tw
e
e
n r
e
s
e
a
r
c
h ke
yw
or
ds
Ide
nt
i
fi
c
a
t
i
on
P
roj
e
c
t
i
on
In
c
l
u
s
i
o
n
Ide
nt
i
fi
e
d
re
c
ords
of:
D
a
t
a
ba
s
e
s
(n
=
2)
S
c
opus
(n
=
265)
P
ubM
e
d
(n
=
8)
Re
c
ords
re
m
ove
d
be
f
or
e
pr
oj
e
c
t
i
on
:
D
upl
i
c
a
t
e
re
c
ords
re
m
ove
d
(n
=
0)
P
roj
e
c
t
e
d
re
c
ords
:
(n
=
273)
E
xc
l
ude
d
re
c
ords
:
(n
=
130)
Re
c
ords
s
ought
for
re
t
ri
e
va
l
:
(n
=
143)
Re
c
ords
not
re
c
ove
re
d:
(n
=
8)
Re
c
ords
e
va
l
ua
t
e
d
for
e
l
i
gi
bi
l
i
t
y
:
(n
=
13
5)
E
xc
l
ude
d
re
c
ords
:
(n
=
95
)
S
t
udi
e
s
i
nc
l
ude
d
i
n
t
he
re
vi
e
w
:
(n
=
40
)
Ide
nt
i
fi
c
a
t
i
on
of
da
t
a
ba
s
e
a
nd
re
gi
s
t
ry
s
t
udi
e
s
ba
s
e
s
a
nd
re
gi
s
t
e
rs
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
Sy
s
te
m
at
ic
r
e
v
ie
w
of
a
r
ti
fi
c
ia
l
in
te
ll
ig
e
nc
e
w
it
h ne
ar
-
in
fr
a
r
e
d i
n
bl
ue
be
r
r
ie
s
…
(
L
is
e
t
C
a
y
hual
la
A
m
ar
o
)
3765
F
ig
ur
e
3
s
how
s
th
e
r
e
pr
e
s
e
nt
a
ti
on
of
th
e
pr
opo
r
ti
on
o
f
th
e
m
a
in
te
r
m
s
th
a
t
in
di
c
a
te
th
e
f
r
e
que
nc
y
o
f
publ
ic
a
ti
on by ye
a
r
of
t
he
a
r
t
ic
le
s
. I
n a
ddi
ti
on, t
he
r
e
la
ti
ons
hi
p
by c
ol
or
c
a
n be
s
e
e
n, w
it
h "
de
e
p l
e
a
r
ni
ng"
a
nd
"
c
he
m
is
tr
y
"
a
s
r
e
c
e
nt
t
e
r
m
s
i
n r
e
s
e
a
r
c
h publi
s
h
e
d i
n t
he
l
a
s
t
ha
l
f
of
2022. T
he
de
ns
it
y of
t
he
ke
y e
le
m
e
nt
s
c
a
n
be
a
ppr
e
c
ia
te
d
w
he
r
e
two
of
th
e
m
os
t
pr
e
dom
in
a
nt
te
r
m
s
w
it
hi
n
th
e
r
e
s
e
a
r
c
h
to
pi
c
c
a
n
be
vi
s
u
a
li
z
e
d
w
hi
c
h
a
r
e
"
ne
a
r
in
f
r
a
r
e
d
s
pe
c
tr
os
c
opy"
a
nd
"
f
r
ui
ts
"
r
e
f
e
r
r
in
g
to
th
e
a
r
ti
c
le
s
th
a
t
in
c
lu
de
th
e
s
e
to
pi
c
s
publ
is
he
d
in
th
e
la
s
t
ye
a
r
s
.
F
ig
ur
e
3. K
e
yw
or
d de
ns
it
y a
na
ly
s
is
of
r
e
s
e
a
r
c
h ke
yw
or
ds
3.2. Ye
ar
of
p
u
b
li
c
at
io
n
T
he
s
e
le
c
te
d
s
tu
di
e
s
w
e
r
e
publ
is
he
d
be
twe
e
n
2019
a
nd
2023.
F
ig
ur
e
4
s
how
s
th
e
num
b
e
r
of
s
tu
di
e
s
publ
is
he
d
w
it
hi
n
th
e
s
e
le
c
te
d
ti
m
e
li
ne
.
O
ve
r
a
ll
,
th
e
ol
de
s
t
s
tu
dy
r
e
vi
e
w
e
d
w
a
s
publ
is
he
d
in
2019,
w
hi
le
in
2022
m
os
t
of
th
e
a
r
t
ic
le
s
w
e
r
e
publ
is
he
d.
O
f
th
os
e
r
e
vi
e
w
e
d,
f
our
a
r
t
ic
le
s
w
e
r
e
publ
is
he
d
in
2019,
f
iv
e
a
r
ti
c
le
s
in
2020,
th
r
e
e
a
r
ti
c
le
s
in
2021,
f
if
te
e
n
a
r
t
ic
le
s
in
202
2,
a
nd
th
ir
te
e
n
a
r
t
ic
le
s
in
2023.
B
a
s
e
d
on
th
e
r
e
s
ul
ts
,
it
is
obs
e
r
ve
d
th
a
t
th
e
la
te
s
t
s
tu
di
e
s
to
uc
h
on
to
pi
c
s
r
e
la
te
d
to
a
ppl
ic
a
ti
on
s
of
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
a
s
one
of
t
he
a
ppr
oa
c
he
s
t
o i
m
pr
ove
t
he
pr
e
di
c
ti
on of
r
e
s
ul
ts
ba
s
e
d on
N
I
R
S
.
F
ig
ur
e
4. N
um
be
r
of
doc
um
e
nt
s
by ye
a
r
of
publi
c
a
ti
on
3.3. B
lu
e
b
e
r
r
y q
u
al
it
y i
n
d
ic
at
or
s
T
he
r
e
s
e
a
r
c
h
que
s
ti
on
s
a
r
e
di
s
c
us
s
e
d
in
th
is
s
e
c
ti
on.
T
he
f
ir
s
t
r
e
s
e
a
r
c
h
que
s
ti
on
a
ddr
e
s
s
e
d
is
:
(
R
Q
1)
W
ha
t
ty
pe
of
bl
ue
be
r
r
y qua
li
ty
in
di
c
a
to
r
s
ha
ve
be
e
n pr
e
di
c
te
d us
in
g m
a
c
hi
ne
l
e
a
r
ni
ng me
th
ods
?
B
a
s
e
d on the
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
. 13, No. 4, D
e
c
e
m
be
r
2024:
3761
-
3771
3766
a
r
ti
c
le
s
r
e
vi
e
w
e
d,
va
r
io
us
in
te
r
na
l
qua
li
ty
in
di
c
a
to
r
s
of
f
r
ui
ts
ha
ve
be
e
n
f
ound
to
be
im
por
ta
nt
in
de
te
r
m
in
in
g
r
ip
e
ne
s
s
.
T
he
s
e
c
a
n
b
e
di
s
ti
nc
t
c
om
pound
s
pr
e
s
e
nt
in
s
id
e
th
e
f
r
ui
t
th
a
t
c
a
n
be
de
te
c
te
d
by
s
p
e
c
tr
os
c
opi
c
m
e
a
ns
or
by
de
s
tr
uc
ti
on
of
th
e
f
r
ui
t
[
17]
–
[
21
]
.
S
om
e
in
te
r
na
l
in
di
c
a
to
r
s
s
uc
h
a
s
s
uga
r
c
ont
e
nt
,
a
c
id
-
s
uga
r
r
a
ti
o,
f
ir
m
ne
s
s
,
te
xt
ur
e
,
a
nd
vi
ta
m
in
C
a
r
e
obt
a
in
e
d
by
tr
a
di
ti
on
a
l
de
s
tr
uc
ti
ve
a
nd
non
-
de
s
tr
uc
ti
ve
m
e
th
ods
to
be
us
e
d
to
de
te
r
m
in
e
th
e
qua
li
ty
o
f
th
e
f
r
ui
t
[
22]
–
[
25]
.
L
ik
e
w
i
s
e
,
a
c
c
or
di
ng
to
P
or
nc
ha
lo
e
m
pong
e
t
al
.
[
26]
,
N
I
R
S
w
a
s
u
s
e
d
to
pr
e
di
c
t
th
e
S
S
C
of
m
a
ngo
e
s
,
w
hi
c
h
in
di
c
a
te
s
th
e
s
w
e
e
tn
e
s
s
of
th
e
pr
oduc
t
a
nd
d
e
te
r
m
in
e
s
w
he
th
e
r
it
m
e
e
t
s
m
a
r
ke
ti
ng
s
ta
nda
r
ds
.
F
ur
th
e
r
m
or
e
,
a
c
c
or
di
ng
to
Z
ha
ng
e
t
al
.
[
23]
,
s
ol
ubl
e
s
ol
id
s
,
f
ir
m
ne
s
s
,
a
nd
a
c
id
it
y
a
r
e
e
s
ta
bl
is
h
e
d
a
s
im
por
ta
nt
in
te
r
na
l
qua
li
ty
c
h
a
r
a
c
t
e
r
is
ti
c
s
.
A
ls
o,
S
S
C
is
a
n
in
di
c
a
to
r
th
a
t
i
s
m
or
e
li
nke
d
to
c
ons
um
e
r
pe
r
c
e
pt
io
n
of
f
r
ui
t
qua
li
ty
[
27]
,
[
28]
.
T
a
bl
e
5
s
how
s
th
a
t
th
e
SSC
in
di
c
a
to
r
i
s
th
e
m
os
t
us
e
d
a
nd
e
v
a
lu
a
te
d
in
r
e
s
e
a
r
c
h
be
c
a
us
e
it
i
s
a
va
lu
e
th
a
t
he
lp
s
to
de
te
r
m
in
e
th
e
c
ont
e
nt
of
in
te
r
na
l
s
uga
r
s
,
a
s
w
e
ll
a
s
ot
he
r
s
ol
ubl
e
c
om
pounds
s
u
c
h
a
s
c
e
r
ta
in
m
in
e
r
a
ls
,
w
hi
c
h
a
r
e
k
e
y
to
d
e
te
r
m
in
e
th
e
qu
a
li
ty
a
nd
r
ip
e
ne
s
s
of
f
r
ui
ts
[
25]
,
[
27]
,
[
29]
–
[
33]
.
A
ls
o,
a
c
c
or
di
ng
to
C
a
i
e
t
al
.
[
34]
,
th
e
pr
e
di
c
ti
on
of
th
e
m
oi
s
tu
r
e
in
di
c
a
to
r
he
lp
s
to
know
th
e
le
ve
l
of
de
hydr
a
ti
on
p
r
e
s
e
nt
in
th
e
f
r
ui
ts
a
nd
th
is
in
tu
r
n
w
a
s
us
e
f
ul
to
de
te
r
m
in
e
how
m
uc
h
th
e
f
r
ui
t
w
a
s
a
f
f
e
c
te
d
in
it
s
te
xt
ur
e
a
nd
f
la
vor
c
ha
r
a
c
te
r
is
ti
c
s
w
hi
c
h
a
r
e
of
f
unda
m
e
nt
a
l
im
por
ta
nc
e
f
or
th
e
f
in
a
l
c
ons
um
e
r
.
S
im
il
a
r
ly
,
th
e
T
A
in
di
c
a
to
r
i
s
us
e
f
ul
to
de
te
r
m
in
e
th
e
a
m
ount
of
c
it
r
ic
a
c
id
c
ont
a
in
e
d
in
th
e
f
r
ui
t,
w
hi
c
h
is
a
n
im
por
ta
nt
f
a
c
to
r
th
a
t
m
a
in
ta
in
s
th
e
ba
la
nc
e
be
twe
e
n s
w
e
e
tn
e
s
s
a
nd
a
c
id
it
y
[
19]
,
[
20]
,
[
26]
,
[
30
]
,
[
35]
,
[
36]
.
I
n
a
ddi
ti
on,
ot
he
r
a
r
ti
c
le
s
ta
lk
a
bout
how
de
te
c
t
th
e
in
di
c
a
to
r
phe
nol
ic
a
c
id
s
to
de
te
r
m
in
e
if
th
e
f
r
ui
t
is
s
us
c
e
pt
ib
le
to
s
poi
la
ge
[
17]
,
[
24
]
.
T
hi
s
he
lp
s
to
pr
ot
e
c
t
f
r
ui
ts
be
c
a
us
e
th
e
hi
ghe
r
th
e
phe
nol
ic
a
c
id
in
di
c
a
to
r
,
th
e
lo
ng
e
r
th
e
pr
e
s
e
r
va
ti
on a
nd
th
e
lo
n
ge
r
th
e
s
he
lf
li
f
e
of
th
e
f
r
ui
t.
V
it
a
m
in
C
is
a
ls
o
de
te
c
te
d a
s
a
n i
ndi
c
a
to
r
t
ha
t,
Y
e
e
t
al
.
[
18]
de
te
r
m
in
e
s
w
he
th
e
r
th
e
f
r
ui
t
c
a
n m
a
in
ta
in
a
de
qua
te
f
r
e
s
hne
s
s
f
or
a
lo
nge
r
t
im
e
de
pe
ndi
ng on it
s
qua
nt
it
y a
nd he
lp
s
t
o pr
e
s
e
r
ve
i
t.
F
in
a
ll
y, t
he
dr
y m
a
tt
e
r
(
D
M
)
a
m
ount
pr
e
s
e
nt
i
n
th
e
f
r
ui
t
is
a
ls
o
ta
ke
n
a
s
a
n
in
di
c
a
to
r
[
37]
.
T
hi
s
in
di
c
a
to
r
d
e
te
r
m
in
e
s
w
he
th
e
r
th
e
f
r
ui
t
c
a
n
m
a
in
ta
in
a
n
a
de
qua
te
f
r
e
s
hne
s
s
f
or
a
lo
nge
r
ti
m
e
.
A
r
a
nge
be
twe
e
n
10%
to
30%
of
th
e
r
e
c
om
m
e
nde
d
pr
e
s
e
nc
e
in
th
e
f
r
ui
t
is
a
ls
o us
e
f
ul
t
o de
te
r
m
in
e
i
ts
m
a
tu
r
it
y
[
38]
, [
39
]
.
T
a
bl
e
5. I
ndi
c
a
to
r
s
f
or
qua
li
ty
a
s
s
e
s
s
m
e
nt
#
Q
ua
l
i
t
y
i
ndi
c
a
t
or
U
ni
t
of
m
e
a
s
ur
e
m
e
nt
Q
ua
nt
i
t
y
A
r
t
i
c
l
e
s
1
S
ol
ubl
e
s
ol
i
ds
c
onc
e
nt
r
a
t
i
on
B
r
i
x
33
[
11]
,
[
18]
–
[
27]
,
[
28]
–
[
31
]
, [
33]
, [
35]
,
[
39
]
–
[
46]
,
[
47]
–
[
52]
2
A
m
ount
of
hum
i
di
t
y
(
C
H
)
%
2
[
34]
, [
48]
3
T
i
t
r
a
t
a
bl
e
a
c
i
di
t
y
%
10
[
11]
, [
19]
, [
20]
, [
24]
, [
26
]
, [
29]
, [
35]
, [
36
]
, [
47]
4
P
he
nol
i
c
a
c
i
ds
(
F
T
)
%
2
[
18]
, [
20]
5
D
r
y
m
a
t
t
e
r
%
6
[
23]
, [
38]
, [
48]
, [
52]
, [
53
]
6
V
i
t
a
m
i
n C
(
V
C
)
%
2
[
18]
, [
19]
3.4. M
os
t
u
s
e
d
m
ac
h
in
e
l
e
ar
n
in
g t
e
c
h
n
iq
u
e
s
T
he
s
e
c
ond
r
e
s
e
a
r
c
h
que
s
ti
on
a
ddr
e
s
s
e
d
w
a
s
th
e
f
ol
lo
w
in
g:
(
R
Q
2)
W
ha
t
a
r
e
th
e
di
f
f
e
r
e
nt
m
a
c
hi
ne
le
a
r
ni
ng
te
c
hni
que
s
th
a
t
ha
ve
be
e
n
a
ppl
ie
d
to
pr
e
di
c
t
bl
ue
be
r
r
y
qua
li
ty
?
B
a
s
e
d
on
th
e
a
na
ly
s
i
s
of
th
e
a
r
ti
c
le
s
,
s
om
e
m
a
c
hi
ne
le
a
r
ni
ng
te
c
hni
que
s
w
e
r
e
id
e
nt
if
ie
d
f
r
om
th
os
e
t
ha
t
ha
ve
be
e
n
a
s
s
oc
ia
t
e
d
w
it
h
3
of
th
e
in
te
r
na
l
qua
li
ty
in
di
c
a
to
r
s
th
a
t
a
r
e
th
e
m
os
t
im
por
ta
nt
f
or
bl
ue
be
r
r
y
qua
li
ty
.
T
a
bl
e
6
s
how
s
f
ir
s
t
th
e
SSC
pr
e
di
c
ti
on
in
di
c
a
to
r
,
th
e
y
im
pl
e
m
e
nt
e
d
a
S
V
M
a
lg
or
it
hm
to
pr
e
di
c
t
th
e
B
r
ix
of
f
r
ui
ts
s
uc
h
a
s
p
e
a
r
s
,
or
a
ng
e
s
,
or
a
nge
s
,
a
nd
pe
a
r
s
[
24]
,
[
29]
,
[
40]
,
[
43
]
,
[
44]
.
T
he
n
w
e
r
e
4
a
r
ti
c
le
s
th
a
t
im
pl
e
m
e
nt
th
e
C
N
N
f
or
S
S
C
pr
e
di
c
ti
on
[
19]
,
[
28]
,
[
30
]
,
[
39]
.
L
e
a
s
t
-
s
qua
r
e
s
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
(
L
S
-
S
V
M
)
ba
s
e
d
m
ode
ls
w
e
r
e
a
ls
o
u
s
e
d
f
or
f
r
ui
t
m
a
tu
r
it
y
c
la
s
s
if
ic
a
ti
on
[
27]
,
[
31]
,
[
33]
,
[
38]
.
A
ls
o
de
ta
il
e
d
a
r
e
m
ode
ls
s
uc
h
a
s
gr
a
ph
c
onvolut
io
na
l
ne
twor
k
(
G
C
N
)
,
KNN,
a
nd
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
s
r
e
gr
e
s
s
io
n
(
S
V
M
R
)
w
hi
c
h
a
r
e
m
ode
ls
th
a
t
he
lp
to
im
pr
ove
r
e
gr
e
s
s
io
n
a
nd
c
la
s
s
if
ic
a
ti
on
pr
obl
e
m
s
by
ha
ndl
in
g
nonl
in
e
a
r
in
put
s
a
s
li
ne
a
r
out
put
s
[
19]
,
[
25]
,
[
29
]
,
[
35]
,
[
42]
.
T
he
n
th
e
r
e
i
s
th
e
TA
c
onc
e
nt
r
a
ti
on
pr
e
di
c
ti
on
in
di
c
a
to
r
, w
hi
c
h
in
th
e
a
r
ti
c
le
s
w
a
s
id
e
nt
if
ie
d
a
s
us
in
g
th
e
ANN
a
lg
or
it
hm
,
w
hi
c
h
is
a
ne
ur
a
l
ne
twor
k
c
om
pos
e
d
of
in
p
ut
la
ye
r
s
w
he
r
e
th
e
s
pe
c
tr
a
da
ta
a
r
e
e
nt
e
r
e
d.
T
he
r
e
is
th
e
hi
dde
n
la
ye
r
w
he
r
e
th
e
c
a
lc
ul
a
ti
on a
nd
pr
oc
e
s
s
in
g a
r
e
pe
r
f
or
m
e
d
a
nd
th
e
out
put
la
ye
r
th
a
t
s
how
s
th
e
%
of
TA
[
26]
,
[
37
]
.
I
n
a
ddi
ti
on,
B
a
s
il
e
e
t
al
.
[
54]
in
di
c
a
te
s
th
a
t
in
c
r
e
a
s
in
g
th
e
hi
dde
n
la
ye
r
s
w
il
l
r
e
s
ul
t
in
a
n
e
r
r
one
ous
pr
e
di
c
ti
on,
a
ls
o
th
e
tr
a
in
in
g
s
houl
d
be
di
vi
de
d
in
to
da
ta
to
tr
a
in
th
e
m
ode
l
a
t
80%
a
nd
da
ta
to
te
s
t
th
e
m
ode
l
a
t
20%
.
A
ls
o,
S
V
M
w
a
s
u
s
e
d
f
or
th
e
c
la
s
s
if
ic
a
ti
on
of
s
w
e
e
tn
e
s
s
of
or
a
nge
s
,
w
hi
c
h
w
e
r
e
c
la
s
s
if
ie
d i
nt
o t
hr
e
e
c
la
s
s
e
s
:
s
w
e
e
t,
m
ix
e
d (
s
w
e
e
t
a
nd s
our
)
,
a
nd s
our
[
35]
.
A
ddi
ti
ona
ll
y, m
ode
ls
s
uc
h a
s
G
C
N
a
nd
C
N
N
a
r
e
a
ls
o
de
ta
il
e
d
in
[
19]
th
e
c
om
bi
na
ti
on
of
th
e
s
e
m
ode
ls
s
how
s
a
n
a
c
c
ur
a
te
pe
r
f
or
m
a
nc
e
in
pr
e
di
c
ti
ng
th
e
in
te
r
na
l
qua
li
ty
pa
r
a
m
e
te
r
s
of
m
a
nda
r
in
s
s
in
c
e
a
r
a
pi
d
a
nd
non
-
de
s
tr
uc
ti
ve
e
va
lu
a
ti
on
is
pe
r
f
or
m
e
d t
o obta
in
t
he
da
ta
.
F
in
a
ll
y
,
w
e
ha
ve
th
e
D
M
pr
e
di
c
ti
on
in
di
c
a
to
r
,
w
hi
c
h
w
a
s
id
e
nt
if
ie
d
in
th
e
a
r
ti
c
le
s
a
s
us
in
g
a
m
ode
l
ba
s
e
d
on
a
r
ti
f
ic
ia
l
ne
ur
a
l
ne
twor
ks
(
A
N
N
)
,
w
hi
c
h
i
s
a
s
ubs
e
t
of
m
a
c
hi
ne
le
a
r
ni
ng
th
a
t
he
lp
s
to
pr
oc
e
s
s
d
a
ta
a
nd s
ol
ve
pr
obl
e
m
s
[
54]
. M
or
e
ove
r
, a
c
c
or
di
ng t
o
P
ut
ti
pi
pa
tk
a
jo
r
n
e
t
al
.
[
37
]
f
or
M
L
a
lg
or
it
hm
s
t
o
ha
ve
be
tt
e
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
Sy
s
te
m
at
ic
r
e
v
ie
w
of
a
r
ti
fi
c
ia
l
in
te
ll
ig
e
nc
e
w
it
h ne
ar
-
in
fr
a
r
e
d i
n
bl
ue
be
r
r
ie
s
…
(
L
is
e
t
C
a
y
hual
la
A
m
ar
o
)
3767
r
e
s
ul
ts
,
s
pe
c
tr
a
l
pr
e
tr
e
a
tm
e
nt
w
it
h
c
a
li
br
a
ti
on
m
ode
ls
s
uc
h
a
s
S
N
V
,
m
odi
f
ie
d
s
in
e
c
os
in
e
a
lg
or
it
hm
(
M
S
C
A
)
s
houl
d
be
pe
r
f
or
m
e
d.
A
ls
o,
S
ube
di
a
nd
W
a
l
s
h
[
52]
m
e
nt
io
ne
d
th
a
t
th
e
A
N
N
m
ode
l
h
a
s
u
s
e
d
a
s
in
gl
e
hi
dd
e
n
la
ye
r
a
r
c
hi
te
c
tu
r
e
,
w
hi
c
h
he
lp
e
d
th
e
pr
e
di
c
ti
on
of
a
tt
r
ib
ut
e
s
s
uc
h
a
s
M
S
a
nd
obt
a
in
e
d
r
e
s
ul
ts
li
ke
th
os
e
a
c
hi
e
ve
d by models
s
uc
h a
s
P
L
S
R
.
T
a
bl
e
6. M
o
s
t
us
e
d m
a
c
hi
ne
l
e
a
r
ni
ng t
e
c
hni
que
s
by qua
li
ty
in
di
c
a
to
r
#
Q
ua
l
i
t
y i
ndi
c
a
t
or
M
L
t
e
c
hni
que
s
Q
ua
nt
i
t
y
A
r
t
i
c
l
e
s
1
S
S
C
pr
e
di
c
t
i
on
S
V
M
5
[
29]
, [
35]
, [
43]
, [
44]
C
N
N
4
[
19]
, [
28]
, [
39]
LS
-
S
V
M
4
[
19]
, [
27]
, [
31]
G
C
N
1
[
33]
K
NN
2
[
29]
, [
35]
S
V
M
R
2
[
25]
, [
42]
L
i
ne
a
r
r
e
gr
e
s
s
i
on m
od
e
l
(
L
R
M
)
1
[
40]
M
ul
t
i
l
a
ye
r
pe
r
c
e
pt
r
on
(
M
L
P
)
1
[
40]
L
i
ne
a
r
di
s
c
r
i
m
i
na
nt
a
na
l
ys
i
s
(
L
D
A
)
2
[
29]
, [
35]
2
P
r
e
di
c
t
i
on of
TA
c
onc
e
nt
r
a
t
i
on
S
V
M
2
[
29]
, [
35]
G
C
N
1
[
19]
C
N
N
1
[
19]
K
NN
2
[
29]
, [
35]
L
D
A
2
[
29]
, [
35]
ANN
3
[
37]
, [
54]
3
D
r
y
m
a
t
t
e
r
pr
e
di
c
t
i
on
ANN
4
[
37]
, [
53]
, [
54]
3.5. Ch
e
m
om
e
t
r
ic
t
e
c
h
n
iq
u
e
s
f
or
p
r
e
d
ic
t
in
g b
lu
e
b
e
r
r
y q
u
al
it
y
T
he
th
ir
d
r
e
s
e
a
r
c
h
que
s
ti
on
th
a
t
w
a
s
a
ddr
e
s
s
e
d
is
th
e
f
ol
lo
w
in
g:
(
R
Q
3)
W
ha
t
a
r
e
th
e
c
he
m
om
e
tr
ic
s
te
c
hni
que
s
us
e
d
in
th
e
pr
e
di
c
ti
on
of
bl
ue
be
r
r
y
qua
li
ty
?
B
a
s
e
d
on
th
e
a
na
ly
s
i
s
of
th
e
a
r
ti
c
le
s
,
s
om
e
c
he
m
om
e
tr
ic
s
ba
s
e
d
t
e
c
hni
que
s
ha
ve
be
e
n
id
e
nt
if
ie
d
to
pr
e
di
c
t
ke
y
in
di
c
a
to
r
s
f
or
de
te
r
m
in
in
g
f
r
ui
t
qua
li
ty
th
r
ough
a
na
ly
s
is
.
A
s
de
ta
il
e
d
in
T
a
bl
e
7,
th
e
te
c
hni
qu
e
s
w
it
h
t
he
hi
ghe
s
t
m
e
nt
io
n
in
th
e
r
e
s
e
a
r
c
h
a
r
e
s
how
n
gr
oupe
d by the
i
ndi
c
a
to
r
t
o be
pr
e
di
c
te
d. S
ta
r
ti
ng w
it
h t
he
pr
e
di
c
ti
on of
SSC
, w
hi
c
h
is
obt
a
in
e
d by e
m
pl
oyi
ng
P
L
S
R
a
m
ong
ot
he
r
te
c
hni
que
s
s
u
c
h
a
s
th
e
a
ppl
ic
a
ti
on
of
P
C
A
to
s
e
a
r
c
h
f
or
di
f
f
e
r
e
nc
e
s
in
s
pe
c
tr
a
l
da
t
a
a
nd
de
ve
lo
p
c
a
li
br
a
ti
on
m
ode
ls
to
be
u
s
e
d
w
it
h
da
t
a
obt
a
in
e
d
by
N
I
R
S
[
17]
,
[
22]
,
[
35]
,
[
41]
.
G
uo
e
t
al
.
[
50]
m
e
nt
io
ne
d
th
a
t
it
is
pos
s
ib
le
to
a
ppl
y
r
e
gr
e
s
s
io
n
w
it
h
m
u
lt
ip
l
e
la
te
nt
va
r
ia
bl
e
s
(
P
L
S
2R
)
to
w
or
k
th
e
N
I
R
S
da
ta
in
a
m
ul
ti
li
ne
a
r
r
e
gr
e
s
s
io
n.
I
n
a
ddi
ti
on,
it
is
de
not
e
d
th
a
t
th
e
pr
e
s
e
nc
e
of
e
nvi
r
onm
e
nt
a
l
noi
s
e
or
e
xt
e
r
na
l
f
a
c
to
r
s
c
a
n
ge
ne
r
a
te
nonl
in
e
a
r
s
pe
c
tr
a
th
a
t
c
oul
d
a
lt
e
r
th
e
e
xpe
c
te
d
r
e
s
ul
ts
s
o
th
a
t
th
e
s
e
a
nom
a
li
e
s
s
houl
d
be
tr
e
a
te
d
w
it
h
c
la
s
s
if
ic
a
ti
on
te
c
hni
que
s
s
u
c
h
a
s
S
V
M
[
11]
,
[
47]
,
[
49]
.
I
n
a
ddi
ti
on,
a
c
c
or
di
ng
to
Y
e
e
t
al
.
[
18
]
de
ta
il
s
th
a
t
p
a
r
ti
a
l
le
a
s
t
s
qua
r
e
s
di
s
c
r
im
in
a
nt
a
na
ly
s
i
s
(
P
L
S
-
D
A
)
s
e
r
ve
s
f
or
qua
li
ta
ti
ve
a
na
ly
s
is
th
a
t
c
a
n
be
us
e
d
to
e
la
bor
a
te
th
e
c
la
s
s
if
ic
a
ti
on
of
f
r
ui
t
m
a
tu
r
it
y
c
ha
r
a
c
te
r
is
ti
c
s
a
nd
a
tt
r
ib
ut
e
s
.
F
ur
th
e
r
m
or
e
,
P
L
S
is
a
m
ul
ti
va
r
ia
te
m
e
th
od
th
a
t
c
a
n
a
ls
o
be
u
s
e
d
f
or
s
pe
c
tr
a
l
da
ta
pr
oc
e
s
s
in
g
a
nd
c
a
n
a
ls
o
a
na
ly
z
e
r
e
dunda
nt
va
r
ia
bl
e
s
to
obt
a
in
m
or
e
de
ta
il
e
d
in
f
or
m
a
ti
on
[
21]
,
[
33]
,
[
40
]
,
[
55]
.
F
in
a
ll
y,
f
or
th
e
pr
e
di
c
ti
on
of
TA
a
nd
DM
co
nc
e
nt
r
a
ti
on,
P
L
S
R
a
nd P
L
S
m
e
th
ods
w
e
r
e
us
e
d t
o m
ode
l
th
e
s
pe
c
tr
a
l
da
ta
obt
a
in
e
d by NI
R
S
t
o
id
e
nt
if
y t
he
r
ip
e
ni
ng
s
ta
ge
s
of
th
e
f
r
ui
ts
a
nd
e
s
ta
bl
is
h
th
e
r
e
la
ti
ons
hi
p
be
t
w
e
e
n
th
e
pr
e
di
c
to
r
va
r
ia
bl
e
s
[
26]
,
[
38]
.
A
ls
o,
a
c
c
or
di
ng
to
Z
e
b
e
t
a
l.
[
35
]
,
P
C
A
is
us
e
d
a
s
a
m
e
th
od
to
r
e
du
c
e
th
e
s
e
t
of
da
ta
th
a
t
c
a
n
be
di
s
pl
a
ye
d
by
th
e
s
pe
c
tr
a
a
nd r
e
duc
e
t
h
e
m
t
o f
e
w
e
r
va
r
ia
bl
e
s
t
o obta
in
a
be
tt
e
r
a
n
a
ly
s
is
of
t
he
m
.
T
a
bl
e
7. M
o
s
t
us
e
d
c
he
m
om
e
tr
ic
t
e
c
hni
que
s
by qua
li
ty
i
ndi
c
a
to
r
#
Q
ua
l
i
t
y i
ndi
c
a
t
or
C
he
m
om
e
t
r
i
c
t
e
c
hni
que
s
Q
ua
nt
i
t
y
A
r
t
i
c
l
e
s
1
S
ol
ubl
e
s
ol
i
ds
c
onc
e
nt
r
a
t
i
on pr
e
di
c
t
i
on
P
a
r
t
i
a
l
l
e
a
s
t
s
qua
r
e
s
r
e
gr
e
s
s
i
on
8
[
11]
, [
17]
, [
22]
, [
28]
, [
35
]
, [
41]
,
[
47]
, [
48]
P
a
r
t
i
a
l
l
e
a
s
t
s
qua
r
e
s
di
s
c
r
i
m
i
na
nt
a
na
l
ys
i
s
1
[
18]
P
r
i
nc
i
pa
l
c
om
pone
nt
a
na
l
ys
i
s
6
[
11]
, [
18]
, [
27]
, [
35]
, [
49
]
P
a
r
t
i
a
l
l
e
a
s
t
s
qua
r
e
s
7
[
29]
, [
30]
, [
33]
, [
40]
, [
46
]
, [
55]
S
pa
r
s
e
pa
r
t
i
a
l
l
e
a
s
t
s
qua
r
e
s
r
e
gr
e
s
s
i
on
(
S
P
L
S
R
)
a
nd
s
pa
r
s
e
pa
r
t
i
a
l
l
e
a
s
t
s
qu
a
r
e
s
m
ul
t
i
nom
i
a
l
r
e
gr
e
s
s
i
on
(
S
P
R
M
R
)
1
[
41]
I
nt
e
r
va
l
pa
r
t
i
a
l
l
e
a
s
t
s
qua
r
e
s
(
i
P
L
S
)
S
uc
c
e
s
s
i
ve
pr
oj
e
c
t
i
on
s
a
l
gor
i
t
hm
(
S
P
A
)
1
1
[
44]
[
50]
2
P
r
e
di
c
t
i
on of
TA
c
onc
e
nt
r
a
t
i
on
P
a
r
t
i
a
l
l
e
a
s
t
s
qua
r
e
s
r
e
gr
e
s
s
i
on
1
[
26]
P
a
r
t
i
a
l
l
e
a
s
t
s
qua
r
e
s
1
[
29]
3
D
r
y
m
a
t
t
e
r
c
onc
e
nt
r
a
t
i
on
pr
e
di
c
t
i
on
P
a
r
t
i
a
l
l
e
a
s
t
s
qu
a
r
e
s
1
[
38]
P
a
r
t
i
a
l
l
e
a
s
t
s
qua
r
e
s
r
e
gr
e
s
s
i
on
3
[
48]
, [
52]
, [
53]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
. 13, No. 4, D
e
c
e
m
be
r
2024:
3761
-
3771
3768
3.6. P
e
r
f
or
m
an
c
e
o
f
m
a
c
h
in
e
l
e
ar
n
in
g m
e
t
h
od
s
T
he
f
our
th
r
e
s
e
a
r
c
h
que
s
ti
on
a
ddr
e
s
s
e
d:
(
R
Q
4)
H
ow
h
a
ve
t
he
pe
r
f
or
m
a
nc
e
m
e
tr
ic
s
of
m
a
c
hi
ne
le
a
r
ni
ng
m
ode
ls
be
e
n
c
ondu
c
te
d
to
pr
e
di
c
t
th
e
in
te
r
na
l
qua
li
ty
of
bl
ue
be
r
r
ie
s
?
B
a
s
e
d
on
th
e
a
na
ly
s
is
of
th
e
a
r
ti
c
le
s
,
pe
r
f
or
m
a
nc
e
m
e
tr
ic
s
th
a
t
a
s
s
e
s
s
th
e
a
c
c
ur
a
c
y
or
pr
e
di
c
ti
ve
a
bi
li
ty
of
a
m
a
c
hi
n
e
le
a
r
ni
ng
m
ode
l
ha
ve
be
e
n
id
e
nt
if
ie
d.
A
s
de
ta
il
e
d
in
T
a
bl
e
8,
th
e
di
f
f
e
r
e
nt
m
e
tr
ic
s
a
d
opt
e
d
a
r
e
s
how
n
.
A
c
c
or
di
ng
to
Z
e
b
e
t
al
.
[
35]
th
e
a
c
c
ur
a
c
y
m
e
tr
ic
w
a
s
us
e
d
to
e
va
lu
a
te
th
e
a
c
c
ur
a
c
y
of
th
e
jo
in
t
S
V
M
+
K
N
N
m
ode
l
w
hi
c
h
w
a
s
us
e
d
to
pr
e
di
c
t
th
e
pe
r
c
e
nt
a
ge
of
S
S
C
in
or
a
nge
s
,
obt
a
in
in
g
a
n
a
c
c
ur
a
c
y
of
81.03%
f
or
th
e
c
la
s
s
if
ic
a
ti
on.
L
ik
e
w
is
e
,
a
c
c
or
di
ng
to
P
our
da
r
ba
ni
e
t
al
.
[
36]
,
th
e
a
c
c
ur
a
c
y
m
e
tr
ic
w
a
s
us
e
d
to
e
va
lu
a
te
th
e
C
N
N
m
ode
l,
w
hi
c
h
obt
a
in
e
d a
n a
c
c
ur
a
c
y of
100%
f
or
t
he
de
te
c
ti
on of
pH
of
a
ppl
e
s
a
nd t
he
c
oe
f
f
ic
ie
nt
o
f
de
te
r
m
in
a
ti
on
w
a
s
0.86
w
hi
c
h
de
te
r
m
in
e
d
th
e
va
r
ia
bi
li
ty
of
th
e
da
ta
f
or
pr
e
di
c
ti
ng
p
H
.
F
ur
th
e
r
m
or
e
,
a
c
c
or
di
ng
to
W
u
e
t
al
.
[
19
]
a
G
C
N
-
L
S
T
M
-
A
T
m
ode
l
w
a
s
us
e
d
to
pr
e
di
c
t
S
S
C
s
in
m
a
nd
a
r
in
s
,
w
hi
c
h
a
c
hi
e
v
e
d
th
e
be
s
t
p
e
r
f
or
m
a
nc
e
c
om
pa
r
e
d t
o ot
he
r
m
ode
ls
.
T
a
bl
e
8. M
od
e
l
pe
r
f
or
m
a
nc
e
e
va
lu
a
ti
on me
tr
ic
s
by qua
li
ty
i
ndi
c
a
to
r
#
Q
ua
l
i
t
y
i
ndi
c
a
t
or
S
e
l
e
c
t
e
d m
ode
l
P
e
r
f
or
m
a
nc
e
m
e
t
r
i
c
s
R
e
s
ul
t
A
r
t
i
c
l
e
1
SSC
S
V
M
a
nd K
N
N
A
c
c
ur
a
c
y (
%
)
81.03
[
35]
2
SSC
G
C
N
-
L
S
T
M
-
AT
R
M
S
E
C
V
R
2
M
A
E
0.1430
0.988
0.119
[
19]
3
pH
ANN
A
c
c
ur
a
c
y (
%
)
R
2
100
0.86
[
36]
4
TA
ANN
A
c
c
ur
a
c
y (
%
)
R
2
99.2
0.86
[
36]
5
SSC
C
N
N
A
c
c
ur
a
c
y (
%
)
97.1
[
39]
6
SSC
LS
-
S
V
M
R
oot
m
e
a
n s
qua
r
e
e
r
r
or
of
pr
e
di
c
t
i
on
(
R
M
S
E
P
)
0.32
[
33]
7
SSC
S
V
M
R
R
2
R
M
S
E
0.95
1.83
[
42]
8
SSC
ANN
R
M
S
E
R
2
0.52
0.82
[
54]
9
SSC
C
N
N
A
c
c
ur
a
c
y (
%
)
R
2
98.9
0.71
[
39]
10
SSC
C
N
N
R
2
R
M
S
E
0.8580
0.4276
[
28]
11
SSC
S
V
M
A
c
c
ur
a
c
y (
%
)
85
[
43]
12
SSC
L
D
A
A
c
c
ur
a
c
y (
%
)
91.43
[
29]
13
SSC
C
N
N
R
2
R
M
S
E
0.87
1.76
[
30]
14
SSC
L
D
A
+S
V
M
A
c
c
ur
a
c
y (
%
)
97.44
[
44]
15
SSC
LS
-
S
V
M
R
2
0.973
[
31]
16
SSC
S
V
M
-
R
R
M
S
E
P
1.6867
[
25]
17
MS
ANN
R
M
S
E
P
0.89
[
53]
18
SSC
B
P
N
N
R
2
R
M
S
E
0.8872
0.4709
[
32]
19
D
e
gr
e
e
of
br
ui
s
i
ng
LS
-
S
V
M
+S
P
A
A
c
c
ur
a
c
y (
%
)
97.3
[
27]
T
he
m
e
tr
ic
s
c
on
s
id
e
r
e
d
to
e
va
lu
a
te
th
e
m
ode
l
w
e
r
e
r
oot
m
e
a
n
s
qua
r
e
e
r
r
or
of
c
r
os
s
-
va
li
da
ti
on
(
R
M
S
E
C
V
)
w
hi
c
h
obt
a
in
e
d
(
0.1430
∘
B
r
ix
)
,
R
2
(
0.988)
,
a
nd
m
e
a
n
a
bs
ol
ut
e
e
r
r
or
(
M
A
E
)
(
0.119
∘
B
r
ix
)
.
L
ik
e
w
is
e
,
a
c
c
or
di
ng
to
G
a
la
l
e
t
al
.
[
42]
,
th
e
m
e
tr
ic
s
c
oe
f
f
ic
ie
nt
of
de
te
r
m
in
a
ti
on
(
R
2
)
a
nd
r
oot
m
e
a
n
s
qu
a
r
e
d
e
r
r
or
(
R
M
S
E
)
w
e
r
e
us
e
d t
o
e
va
lu
a
te
t
he
e
f
f
e
c
ti
ve
ne
s
s
of
t
he
S
V
M
R
m
ode
ls
f
or
t
he
e
va
lu
a
ti
on o
f
ba
na
na
s
a
nd
A
N
N
f
or
th
e
e
va
lu
a
ti
on
of
gr
a
pe
s
,
w
hi
c
h
obt
a
in
e
d
a
be
tt
e
r
pe
r
f
or
m
a
nc
e
f
or
th
e
pr
e
di
c
ti
on
of
s
ol
ubl
e
s
ol
id
s
,
f
or
th
e
S
V
M
R
m
ode
l
a
V
(
0.95)
,
R
M
S
E
(
1.83
)
w
a
s
obt
a
in
e
d
a
nd
th
e
A
N
N
m
ode
l
obt
a
in
e
d
a
R
2
(
0.95)
,
R
M
S
E
(
1.83)
.
I
n a
ddi
ti
on,
E
s
c
á
r
a
te
e
t
al
.
[
39]
th
e
e
s
ti
m
a
ti
on of
s
ol
ubl
e
s
ol
id
s
i
n s
to
ne
f
r
ui
ts
i
s
pe
r
f
or
m
e
d,
f
o
r
th
is
pur
pos
e
a
m
ode
l
ba
s
e
d
on
C
N
N
w
a
s
pe
r
f
or
m
e
d,
w
hi
c
h
ob
t
a
in
e
d
a
pe
r
f
or
m
a
nc
e
of
a
c
c
ur
a
c
y
(
98.9
%
)
a
nd
R
2
(
0.71)
c
om
pa
r
e
d t
o t
he
ot
he
r
m
ode
ls
. L
ik
e
w
is
e
, a
c
c
or
di
ng t
o X
u
e
t
al
.
[
28]
pe
r
f
o
r
m
a
nc
e
of
t
he
C
N
N
-
ba
s
e
d
m
ode
l
f
or
th
e
pr
e
di
c
ti
on
of
S
S
C
in
or
a
nge
s
w
a
s
e
va
lu
a
te
d
a
nd
th
e
r
e
s
ul
ts
w
e
r
e
R
2
(
0.8580)
a
nd
R
M
S
E
(
0.4276)
.
I
n
a
ddi
t
io
n,
a
c
c
or
di
ng
to
L
a
z
im
e
t
al
.
[
43
]
th
e
S
V
M
-
ba
s
e
d
m
ode
l
w
a
s
e
v
a
lu
a
te
d
f
or
th
e
pr
e
di
c
ti
on
of
S
S
C
a
nd
c
la
s
s
if
ic
a
ti
on
of
w
a
te
r
m
e
lo
n
m
a
tu
r
it
y
le
ve
l,
obt
a
in
i
ng
a
r
e
s
ul
t
of
85%
a
c
c
ur
a
c
y.
T
he
L
D
A
m
ode
l
w
a
s
a
ls
o
e
v
a
lu
a
te
d
f
or
m
a
ngo
m
a
tu
r
it
y
le
ve
l
pr
e
di
c
ti
on,
w
he
r
e
th
e
A
c
c
ur
a
c
y
pe
r
f
or
m
a
nc
e
m
e
tr
ic
w
a
s
u
s
e
d
a
nd
obt
a
in
e
d
a
r
e
s
ul
t
of
91.43%
[
29]
.
L
ik
e
w
is
e
,
a
c
c
or
di
ng
to
K
a
lo
pe
s
a
e
t
al
.
[
30]
th
e
C
N
N
m
ode
l
is
us
e
d
f
or
th
e
e
s
ti
m
a
ti
on
of
s
uga
r
c
ont
e
nt
in
gr
a
pe
s
,
ha
vi
ng
a
n
e
va
lu
a
ti
on
of
th
e
m
ode
l
a
n
R
2
(
0.87)
,
R
M
S
E
(
1.76)
.
R
e
s
e
a
r
c
h by L
a
m
pt
e
y
e
t
al
.
[
44]
th
e
L
D
A
-
S
V
M
m
ode
l
w
a
s
e
va
lu
a
te
d f
or
t
he
c
la
s
s
if
ic
a
ti
on of
m
a
ngoe
s
w
he
r
e
a
n
a
c
c
ur
a
c
y
of
97.44%
w
a
s
obt
a
in
e
d,
how
e
ve
r
,
if
id
e
nt
if
ic
a
ti
on
te
c
hni
que
s
s
uc
h
a
s
m
e
a
n
c
e
nt
e
r
in
g
(
M
C
)
,
S
N
V
,
f
ir
s
t
de
r
iv
a
ti
ve
(
F
D
)
,
a
nd
s
e
c
ond
de
r
iv
a
ti
ve
(
S
D
)
a
r
e
us
e
d,
a
hi
ghe
r
pe
r
c
e
nt
a
g
e
of
a
c
c
ur
a
c
y
c
oul
d
be
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
Sy
s
te
m
at
ic
r
e
v
ie
w
of
a
r
ti
fi
c
ia
l
in
te
ll
ig
e
nc
e
w
it
h ne
ar
-
in
fr
a
r
e
d i
n
bl
ue
be
r
r
ie
s
…
(
L
is
e
t
C
a
y
hual
la
A
m
ar
o
)
3769
a
c
hi
e
ve
d.
F
in
a
ll
y,
S
ha
o
e
t
al
.
[
27]
th
e
c
om
bi
na
ti
on
of
L
S
-
S
V
M
m
ode
ls
w
a
s
us
e
d
f
or
th
e
c
la
s
s
if
ic
a
ti
on
of
c
he
r
r
ie
s
ba
s
e
d
on
th
e
d
e
gr
e
e
of
br
ui
s
in
g,
w
hi
c
h
r
e
s
ul
te
d
in
a
n
a
c
c
ur
a
c
y
of
97%
.
T
h
e
f
ol
lo
w
in
g
r
e
vi
e
w
s
h
a
ve
s
how
n
th
a
t
s
e
ve
r
a
l
ty
pe
s
of
A
I
te
c
hni
que
s
ha
ve
be
e
n
a
ppl
ie
d
f
or
pr
e
di
c
ti
on
a
nd
di
f
f
e
r
e
nt
m
e
tr
ic
s
f
or
e
va
lu
a
ti
ng
th
e
pe
r
f
or
m
a
nc
e
of
th
e
m
ode
ls
,
w
hi
c
h
d
e
m
ons
tr
a
te
d
a
c
or
r
e
c
t
r
e
s
ul
t
in
th
e
pr
e
c
is
io
n
of
th
e
di
f
f
e
r
e
nt
e
va
lu
a
te
d c
he
m
ic
a
l
a
s
p
e
c
ts
of
a
f
r
ui
t.
4.
C
O
N
C
L
U
S
I
O
N
T
hi
s
s
tu
dy
pr
e
s
e
nt
e
d
a
s
y
s
te
m
a
ti
c
r
e
vi
e
w
of
th
e
li
te
r
a
tu
r
e
a
bo
ut
how
th
e
a
ppl
ic
a
ti
on
of
N
I
R
S
w
it
h
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
in
c
onj
unc
ti
on
w
i
th
c
he
m
om
e
tr
ic
s
a
ll
ow
s
th
e
a
na
ly
s
is
a
nd
e
va
lu
a
ti
on
of
th
e
qua
li
ty
o
f
bl
ue
be
r
r
ie
s
a
nd
ot
he
r
f
r
ui
ts
.
T
he
qua
li
ty
of
th
e
s
e
f
r
ui
ts
c
a
n
va
r
y
due
to
va
r
io
us
hum
a
n
a
nd
e
nvi
r
onm
e
nt
a
l
f
a
c
to
r
s
f
r
om
t
he
p
r
oduc
ti
on s
ta
ge
t
o t
he
di
s
tr
ib
ut
io
n a
nd c
ons
u
m
pt
io
n s
ta
ge
. T
he
i
m
por
ta
nc
e
of
unde
r
s
ta
ndi
ng
qua
li
ty
w
il
l
im
pr
ove
c
ons
um
e
r
s
a
ti
s
f
a
c
ti
on
a
nd
a
ll
ow
f
r
ui
ts
to
be
pr
e
s
e
r
ve
d
in
th
e
ir
opt
im
a
l
s
t
a
te
of
c
ons
um
pt
io
n.
R
e
c
e
nt
obs
e
r
va
ti
ons
s
ugg
e
s
t
th
a
t
th
e
w
a
y
to
a
na
l
ys
is
of
th
e
qu
a
li
ty
of
th
e
f
r
ui
t
is
done
th
r
ough
te
c
hni
que
s
s
u
c
h a
s
N
I
R
S
, c
h
e
m
om
e
tr
ic
s
, a
nd
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
m
ode
ls
t
ha
t
s
e
e
k t
o i
m
pr
ove
t
he
t
r
a
di
ti
ona
l
w
a
ys
of
in
te
r
na
l
e
va
lu
a
ti
on
of
th
e
qua
li
ty
of
bl
ue
be
r
r
ie
s
a
nd
f
i
nd
r
e
la
ti
ons
hi
ps
be
twe
e
n
th
e
a
na
ly
z
e
d
s
pe
c
tr
a
a
nd t
he
° B
r
ix
o
f
bl
ue
be
r
r
ie
s
. L
ik
e
w
is
e
, our
r
e
s
e
a
r
c
h pr
ovi
de
s
c
onc
lu
s
iv
e
e
vi
de
nc
e
t
ha
t
th
e
i
m
pl
e
m
e
nt
a
ti
on of
pr
e
di
c
ti
ve
m
ode
ls
f
or
th
e
pr
e
di
c
ti
on
of
S
S
C
in
bl
ue
b
e
r
r
ie
s
a
nd
ot
he
r
ty
pe
s
of
f
r
ui
ts
a
c
hi
e
ve
d
a
good
r
e
s
ul
t
in
qua
li
ty
e
va
lu
a
ti
on.
T
hi
s
s
tu
dy
is
e
xpe
c
te
d
to
c
ont
r
ib
ut
e
knowle
dge
f
or
f
ut
ur
e
r
e
s
e
a
r
c
h
w
or
k
on
how
th
e
a
ppl
ic
a
ti
on
of
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
,
N
I
R
S
,
a
nd
c
he
m
om
e
tr
ic
s
c
a
n
pr
ovi
de
be
tt
e
r
w
a
ys
to
de
te
r
m
in
e
th
e
qua
li
ty
of
f
r
ui
ts
, i
nc
lu
di
ng blue
be
r
r
ie
s
.
R
E
F
E
R
E
N
C
E
S
[
1]
Y
.
L
i
u
e
t
al
.
,
“
‘
I
s
t
hi
s
bl
ue
be
r
r
y
r
i
pe
?
’
:
a
bl
ue
be
r
r
y
r
i
pe
ne
s
s
de
t
e
c
t
i
on
a
l
gor
i
t
hm
f
or
us
e
on
pi
c
ki
ng
r
obot
s
,”
F
r
ont
i
e
r
s
i
n
P
l
ant
Sc
i
e
nc
e
, vol
. 14, 2023, doi
:
10.3389/
f
pl
s
.2023.1198650.
[
2]
W
.
Y
a
ng,
X
.
M
a
,
a
nd
H
.
A
n,
“
B
l
ue
be
r
r
y
r
i
pe
ne
s
s
de
t
e
c
t
i
on
m
ode
l
ba
s
e
d
on
e
nha
nc
e
d
de
t
a
i
l
f
e
a
t
ur
e
a
nd
c
ont
e
nt
-
a
w
a
r
e
r
e
a
s
s
e
m
bl
y,”
A
gr
onom
y
, vol
. 13, no. 6, 2023, doi
:
10.3390/
a
gr
onom
y13061613
.
[
3]
Y
.
B
a
i
,
Y
.
F
a
ng,
B
.
Z
ha
ng,
a
nd
S
.
F
a
n,
“
M
ode
l
r
obus
t
ne
s
s
i
n
e
s
t
i
m
a
t
i
on
of
bl
u
e
be
r
r
y
S
S
C
us
i
ng
N
I
R
S
,”
C
om
put
E
l
e
c
t
r
on
A
gr
i
c
,
vol
. 198, 2022, doi
:
10.1016/
j
.c
om
pa
g.2022.107073.
[
4]
H
.
Y
a
ng
e
t
al
.
,
“
T
r
a
ns
c
r
i
pt
om
i
c
a
nd
m
e
t
a
bol
om
i
c
p
r
of
i
l
i
ng
r
e
ve
a
l
s
t
he
va
r
i
a
t
i
ons
i
n
c
a
r
bohydr
a
t
e
m
e
t
a
bol
i
s
m
be
t
w
e
e
n
t
w
o
bl
ue
be
r
r
y c
ul
t
i
va
r
s
,”
I
nt
e
r
nat
i
onal
J
our
nal
of
M
ol
e
c
ul
ar
Sc
i
e
nc
e
s
, vol
. 25, no.
1, 2024, doi
:
10.3390/
i
j
m
s
25010293.
[
5]
M
.
V
.
-
C
a
s
t
e
l
l
ot
e
,
D
.
P
.
-
M
a
r
í
n,
I
.
T
.
-
R
odr
í
gue
z
,
J
.
M
.
M
.
-
R
oj
a
s
,
J
.
L
.
O
.
-
D
í
a
z
,
a
nd
M
.
T
.
S
á
nc
he
z
,
“
G
r
e
e
n,
m
ul
t
i
va
r
i
a
t
e
a
ppr
oa
c
h
f
or
obt
a
i
ni
ng
a
f
i
nge
r
pr
i
nt
of
qua
l
i
t
y
of
w
a
t
e
r
m
e
l
ons
a
t
s
upe
r
m
a
r
ke
t
l
e
ve
l
us
i
ng
ne
a
r
i
nf
r
a
r
e
d
s
pe
c
t
r
os
c
opy,”
L
W
T
,
vol
.
182, 2023, doi
:
10.1016/
j
.l
w
t
.2023.114831.
[
6]
M
.
T
.
S
.
-
B
a
l
l
e
s
t
a
,
C
.
M
.
-
A
nde
r
s
,
M
.
D
.
Á
l
va
r
e
z
,
M
.
I
. E
s
c
r
i
ba
no,
C
.
M
e
r
odi
o,
a
nd
I
.
R
om
e
r
o,
“
A
r
e
t
he
bl
ue
be
r
r
i
e
s
w
e
buy
good
qua
l
i
t
y?
C
om
pa
r
a
t
i
ve
s
t
udy
of
be
r
r
i
e
s
pur
c
ha
s
e
d
f
r
om
di
f
f
e
r
e
nt
ou
t
l
e
t
s
,”
F
oods
,
vol
.
12,
no.
13,
2023,
doi
:
10.3390/
f
oods
12132621.
[
7]
A
.
A
.
-
C
e
r
e
z
o,
X
.
Y
a
ng,
A
.
M
.
J
.
-
C
a
r
ve
l
o,
M
.
P
e
l
l
e
gr
i
no,
A
.
F
.
S
a
vi
no,
a
nd
P
.
B
e
r
z
a
ghi
,
“
A
s
s
e
s
s
m
e
nt
of
e
xt
r
a
vi
r
gi
n
ol
i
ve
oi
l
qua
l
i
t
y
by
m
i
ni
a
t
ur
i
z
e
d
ne
a
r
i
nf
r
a
r
e
d
i
ns
t
r
um
e
nt
s
i
n
a
r
a
pi
d
a
nd
non
-
de
s
t
r
uc
t
i
v
e
pr
oc
e
dur
e
,”
F
ood
C
he
m
i
s
t
r
y
,
vol
.
430,
2024,
doi
:
10.1016/
j
.f
oodc
he
m
.2023.137043.
[
8]
C
.
S
.
P
.
S
a
nt
os
e
t
al
.
,
“
N
on
-
de
s
t
r
uc
t
i
ve
m
e
a
s
ur
e
m
e
nt
of
t
he
i
nt
e
r
na
l
qu
a
l
i
t
y
of
c
i
t
r
us
f
r
ui
t
s
us
i
ng
a
por
t
a
bl
e
N
I
R
de
vi
c
e
,”
J
our
na
l
of
A
O
A
C
I
nt
e
r
nat
i
onal
, vol
. 104, no. 1, pp. 61
–
67, 2021, doi
:
10.1093/
j
a
oa
c
i
nt
/
qs
a
a
115.
[
9]
M
.
L
.
M
ont
e
c
c
hi
a
r
i
ni
e
t
al
.
,
“
P
r
ot
e
om
i
c
a
nd
m
e
t
a
bol
om
i
c
a
ppr
oa
c
he
s
unve
i
l
r
e
l
e
va
nt
bi
oc
he
m
i
c
a
l
c
ha
nge
s
i
n
c
a
r
bohydr
a
t
e
a
nd
c
e
l
l
w
a
l
l
m
e
t
a
bol
i
s
m
s
of
t
w
o
bl
ue
be
r
r
y
(
V
a
c
c
i
ni
um
c
or
ym
bos
um
)
va
r
i
e
t
i
e
s
w
i
t
h
di
f
f
e
r
e
nt
qua
l
i
t
y
a
t
t
r
i
but
e
s
,”
P
l
ant
P
hy
s
i
ol
ogy
and B
i
oc
he
m
i
s
t
r
y
, vol
. 136, pp. 230
–
244, 2019, doi
:
10.1016/
j
.pl
a
phy.2018.12.019.
[
10]
P
.
R
ungpi
c
ha
ya
pi
c
he
t
,
B
.
M
a
ha
yot
he
e
,
M
.
N
a
gl
e
,
P
.
K
huw
i
j
i
t
j
a
r
u,
a
nd
J
.
M
ül
l
e
r
,
“
R
obus
t
N
I
R
S
m
ode
l
s
f
or
non
-
de
s
t
r
uc
t
i
ve
pr
e
di
c
t
i
on
of
pos
t
ha
r
ve
s
t
f
r
ui
t
r
i
pe
ne
s
s
a
nd
qua
l
i
t
y
i
n
m
a
ngo,”
P
os
t
har
v
e
s
t
B
i
ol
ogy
and
T
e
c
hnol
ogy
,
vol
.
111,
pp.
31
–
40,
2016,
doi
:
10.1016/
j
.pos
t
ha
r
vbi
o.2015.07.006.
[
11]
G
.
F
e
r
r
a
r
a
,
V
.
M
a
r
c
ot
ul
i
,
A
.
D
i
donna
,
A
.
M
.
S
t
e
l
l
a
c
c
i
,
M
.
P
a
l
a
s
c
i
a
no,
a
nd
A
.
M
a
z
z
e
o,
“
R
i
p
e
ne
s
s
pr
e
di
c
t
i
on
i
n
t
a
bl
e
gr
a
p
e
c
ul
t
i
va
r
s
by us
i
ng a
por
t
a
bl
e
N
I
R
de
vi
c
e
,”
H
or
t
i
c
ul
t
ur
ae
, vol
. 8, no. 7, 2022, do
i
:
10.3390/
hor
t
i
c
ul
t
ur
a
e
8070613.
[
12]
S
.
D
i
t
c
ha
r
oe
n
e
t
al
.
,
“
I
m
pr
ovi
ng
t
he
non
-
de
s
t
r
uc
t
i
ve
m
a
t
ur
i
t
y
c
l
a
s
s
i
f
i
c
a
t
i
on
m
ode
l
f
or
dur
i
a
n
f
r
ui
t
us
i
ng
ne
a
r
-
i
nf
r
a
r
e
d
s
pe
c
t
r
os
c
opy,”
A
r
t
i
f
i
c
i
al
I
nt
e
l
l
i
ge
nc
e
i
n A
gr
i
c
ul
t
ur
e
, vol
. 7, pp. 35
–
43, 2023, do
i
:
10.1016/
j
.a
i
i
a
.2023.02.002.
[
13]
A
.
E
l
da
w
l
a
t
l
y,
H
.
A
l
s
he
hr
i
,
A
.
A
l
qa
ht
a
ni
,
A
.
A
hm
a
d,
F
.
A
l
-
D
a
m
m
a
s
,
a
nd
A
.
M
a
r
z
ouk,
“
A
ppe
a
r
a
nc
e
of
popul
a
t
i
on,
i
nt
e
r
ve
nt
i
on,
c
om
pa
r
i
s
on,
a
nd
out
c
om
e
a
s
r
e
s
e
a
r
c
h
que
s
t
i
on
i
n
t
he
t
i
t
l
e
of
a
r
t
i
c
l
e
s
of
t
hr
e
e
di
f
f
e
r
e
nt
a
ne
s
t
he
s
i
a
j
our
na
l
s
:
A
pi
l
ot
s
t
udy,”
Saud
i
J
our
nal
of
A
nae
s
t
he
s
i
a,
vol
. 12, no. 2, pp. 283
-
286,
2018
,
doi
:
10.4103/
s
j
a
.S
J
A
_767_17.
[
14]
M
.
J
.
P
a
ge
e
t
al
.
,
“
D
e
c
l
a
r
a
c
i
ón
P
R
I
S
M
A
2020:
una
guí
a
a
c
t
ua
l
i
z
a
da
pa
r
a
l
a
publ
i
c
a
c
i
ón
de
r
e
vi
s
i
one
s
s
i
s
t
e
m
á
t
i
c
a
s
,”
R
e
v
i
s
t
a
E
s
pañol
a de
C
ar
di
ol
ogí
a
, vol
. 74, no. 9, pp. 790
–
799, S
e
p. 2021, doi
:
10.1016/
j
.r
e
c
e
s
p.2021.06.016.
[
15]
N
.
D
ont
hu,
S
.
K
um
a
r
,
D
.
M
ukhe
r
j
e
e
,
N
.
P
a
nde
y,
a
nd
W
.
M
.
L
i
m
,
“
H
ow
t
o
c
onduc
t
a
bi
bl
i
om
e
t
r
i
c
a
na
l
ys
i
s
:
A
n
ove
r
vi
e
w
a
nd
gui
de
l
i
ne
s
,”
J
our
nal
of
B
us
i
ne
s
s
R
e
s
e
ar
c
h
, vol
. 133, pp. 285
–
296, 2021, doi
:
1
0.1016/
j
.j
bus
r
e
s
.2021.04.070.
[
16]
A
.
P
.
-
R
odr
i
gue
z
,
L
.
W
a
l
t
m
a
n,
a
nd
N
.
J
.
va
n
E
c
k,
“
C
ons
t
r
uc
t
i
ng
bi
bl
i
om
e
t
r
i
c
ne
t
w
or
ks
:
A
c
om
pa
r
i
s
on
be
t
w
e
e
n
f
ul
l
a
nd
f
r
a
c
t
i
ona
l
c
ount
i
ng,”
J
our
nal
of
I
nf
or
m
e
t
r
i
c
s
, vol
. 10, no. 4, pp. 1178
–
1195, 2016, doi
:
10
.1016/
j
.j
oi
.2016.10.006.
[
17]
M
.
M
a
nc
i
ni
e
t
al
.
,
“
A
ppl
i
c
a
t
i
on
of
ne
a
r
i
nf
r
a
r
e
d
s
pe
c
t
r
os
c
opy
f
or
t
he
r
a
p
i
d
a
s
s
e
s
s
m
e
nt
of
nut
r
i
t
i
ona
l
qua
l
i
t
y
of
di
f
f
e
r
e
nt
s
t
r
a
w
be
r
r
y c
ul
t
i
va
r
s
,”
F
oods
, vol
. 12, no. 17, 2023, doi
:
10.3390/
f
oods
12173253.
[
18]
W
.
Y
e
,
W
.
X
u,
T
.
Y
a
n,
J
.
Y
a
n,
P
.
G
a
o,
a
nd
C
.
Z
ha
ng,
“
A
ppl
i
c
a
t
i
on
of
ne
a
r
-
i
nf
r
a
r
e
d
s
pe
c
t
r
os
c
opy
a
nd
hype
r
s
pe
c
t
r
a
l
i
m
a
gi
n
g
c
om
bi
ne
d
w
i
t
h
m
a
c
hi
ne
l
e
a
r
ni
ng
a
l
gor
i
t
hm
s
f
or
qua
l
i
t
y
i
ns
pe
c
t
i
on
of
gr
a
pe
:
a
r
e
vi
e
w
,”
F
oods
,
vol
.
12,
no.
1,
2023,
doi
:
10.3390/
f
oods
12010132.
[
19]
Y
.
W
u,
X
.
Z
hu,
Q
.
H
ua
ng,
Y
.
Z
ha
ng,
J
.
E
va
ns
,
a
nd
S
.
H
e
,
“
P
r
e
di
c
t
i
ng
t
he
qua
l
i
t
y
of
t
a
nge
r
i
ne
s
u
s
i
ng
t
he
G
C
N
N
-
L
S
T
M
-
A
T
ne
t
w
or
k ba
s
e
d on V
i
s
–
N
I
R
s
pe
c
t
r
os
c
opy,
”
A
ppl
i
e
d Sc
i
e
nc
e
s
, vol
. 13, no. 14, 20
23, doi
:
10.3390/
a
pp13148221.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
. 13, No. 4, D
e
c
e
m
be
r
2024:
3761
-
3771
3770
[
20]
B
. H
a
s
a
nz
a
de
h,
Y
.
A
.
-
G
i
l
a
nde
h,
A
. S
.
-
N
a
z
a
r
l
oo, E
. D
.
L.
C
.
-
G
á
m
e
z
,
J
. L
.
H
.
-
H
e
r
ná
nde
z
, a
nd
M
.
M
.
-
A
r
r
oyo, “
N
on
-
de
s
t
r
uc
t
i
v
e
m
e
a
s
ur
e
m
e
nt
of
qua
l
i
t
y
pa
r
a
m
e
t
e
r
s
of
a
ppl
e
f
r
ui
t
by
us
i
ng
vi
s
i
bl
e
/
ne
a
r
-
i
nf
r
a
r
e
d
s
pe
c
t
r
os
c
opy
a
nd
m
ul
t
i
va
r
i
a
t
e
r
e
gr
e
s
s
i
on
a
na
l
ys
i
s
,”
Su
s
t
ai
nabi
l
i
t
y
, vol
. 14, no. 22, 2022, doi
:
10.3390/
s
u142214918.
[
21]
C
.
G
uo,
J
.
Z
ha
ng,
W
.
C
a
i
,
a
nd
X
.
S
ha
o,
“
E
nha
nc
i
ng
t
r
a
ns
f
e
r
a
bi
l
i
t
y
of
ne
a
r
-
i
nf
r
a
r
e
d
s
pe
c
t
r
a
l
m
ode
l
s
f
or
s
ol
ubl
e
s
ol
i
ds
c
ont
e
nt
pr
e
di
c
t
i
on a
c
r
os
s
di
f
f
e
r
e
nt
f
r
ui
t
s
,”
A
ppl
i
e
d Sc
i
e
nc
e
s
, vol
. 13, no. 9, 2023, doi
:
10.3390/
a
pp13095417.
[
22]
M
.
É
ge
i
e
t
al
.
,
“
P
r
e
di
c
t
i
on
of
s
ol
ubl
e
s
ol
i
ds
a
nd
l
yc
op
e
ne
c
ont
e
nt
of
pr
oc
e
s
s
i
ng
t
om
a
t
o
c
ul
t
i
va
r
s
by
V
i
s
-
N
I
R
s
pe
c
t
r
os
c
opy,”
F
r
ont
i
e
r
s
i
n N
ut
r
i
t
i
on
, vol
. 9, 2022, doi
:
10.3389/
f
nut
.2022.845317.
[
23]
Y
.
Z
ha
ng,
J
.
F
.
N
oc
k,
Y
.
A
l
S
hof
f
e
,
a
nd
C
.
B
.
W
a
t
ki
ns
,
“
N
on
-
de
s
t
r
uc
t
i
ve
pr
e
di
c
t
i
on
of
s
ol
ubl
e
s
ol
i
ds
a
nd
dr
y
m
a
t
t
e
r
c
ont
e
nt
s
i
n
e
i
ght
a
ppl
e
c
ul
t
i
va
r
s
us
i
ng
ne
a
r
-
i
nf
r
a
r
e
d
s
pe
c
t
r
os
c
opy,”
P
os
t
har
v
e
s
t
B
i
ol
ogy
a
nd
T
e
c
hnol
ogy
,
vol
.
151,
pp.
111
–
118,
2019,
doi
:
10.1016/
j
.pos
t
ha
r
vbi
o.2019.01.009.
[
24]
J
.
A
.
M
a
r
t
i
ns
e
t
al
.
,
“
S
pe
c
t
r
a
N
e
t
–
53:
A
de
e
p
r
e
s
i
dua
l
l
e
a
r
ni
ng
a
r
c
hi
t
e
c
t
ur
e
f
o
r
pr
e
di
c
t
i
ng
s
ol
ubl
e
s
ol
i
ds
c
ont
e
nt
w
i
t
h
V
I
S
–
N
I
R
s
pe
c
t
r
os
c
opy,”
C
om
put
e
r
s
and E
l
e
c
t
r
oni
c
s
i
n A
gr
i
c
ul
t
u
r
e
, vol
. 197, 2022, doi
:
10.1016/
j
.c
om
pa
g.2022.106945.
[
25]
S
.
S
a
r
ka
r
,
J
.
K
.
B
a
s
a
k,
B
.
E
.
M
oon,
a
nd
H
.
T
.
K
i
m
,
“
A
c
om
pa
r
a
t
i
ve
s
t
udy
of
P
L
S
R
a
nd
S
V
M
-
R
w
i
t
h
va
r
i
ous
pr
e
pr
oc
e
s
s
i
n
g
t
e
c
hni
que
s
f
or
t
he
qua
nt
i
t
a
t
i
ve
de
t
e
r
m
i
na
t
i
on
of
s
ol
ubl
e
s
ol
i
ds
c
ont
e
nt
of
ha
r
d
y
ki
w
i
f
r
ui
t
by
a
por
t
a
bl
e
V
i
s
/
N
I
R
s
pe
c
t
r
om
e
t
e
r
,”
F
oods
, vol
. 9, no. 8, 2020, doi
:
10.3390/
f
oods
9081078.
[
26]
P
.
P
or
nc
ha
l
oe
m
pong
e
t
al
.
,
“
N
on
-
de
s
t
r
uc
t
i
ve
qu
a
l
i
t
y
e
va
l
ua
t
i
on
of
t
r
opi
c
a
l
f
r
ui
t
(
m
a
ngo
a
nd
m
a
ngos
t
e
e
n)
pur
é
e
us
i
ng
ne
a
r
-
i
nf
r
a
r
e
d
s
pe
c
t
r
os
c
opy
c
om
bi
ne
d
w
i
t
h
p
a
r
t
i
a
l
l
e
a
s
t
s
qua
r
e
s
r
e
gr
e
s
s
i
on,
”
A
gr
i
c
ul
t
ur
e
,
vol
.
12,
no.
12,
2022,
doi
:
10.3390/
a
gr
i
c
ul
t
ur
e
12122060.
[
27]
Y
.
S
ha
o,
G
.
X
ua
n,
Z
.
H
u,
Z
.
G
a
o,
a
nd
L
.
L
i
u,
“
D
e
t
e
r
m
i
na
t
i
on
of
t
he
br
ui
s
e
de
gr
e
e
f
or
c
he
r
r
y
us
i
ng
V
i
s
-
N
I
R
r
e
f
l
e
c
t
i
on
s
pe
c
t
r
os
c
opy c
oupl
e
d w
i
t
h m
ul
t
i
va
r
i
a
t
e
a
na
l
y
s
i
s
,”
P
L
oS O
N
E
, vol
. 14, no. 9, 2019, doi
:
10.1371/
j
our
na
l
.pone
.0222633.
[
28]
S
.
X
u,
H
.
L
u,
C
.
F
e
r
e
nc
e
,
a
nd
Q
.
Z
ha
ng,
“
A
n
a
c
c
ur
a
c
y
i
m
pr
ove
m
e
nt
m
e
t
hod
ba
s
e
d
on
m
ul
t
i
-
s
our
c
e
i
nf
o
r
m
a
t
i
on
f
us
i
on
a
nd
de
e
p
l
e
a
r
ni
ng
f
or
t
s
s
c
a
nd
w
a
t
e
r
c
ont
e
nt
nonde
s
t
r
uc
t
i
ve
de
t
e
c
t
i
on
i
n
‘
l
uoga
ng’
or
a
ng
e
,”
E
l
e
c
t
r
oni
c
s
,
vol
.
10,
no.
1,
pp.
1
–
12,
2021,
doi
:
10.3390/
e
l
e
c
t
r
oni
c
s
10010080.
[
29]
A
.
K
hum
a
i
di
,
Y
.
A
.
P
u
r
w
a
nt
o,
H
.
S
ukoc
o,
a
nd
S
.
H
.
W
i
j
a
ya
,
“
U
s
i
ng
f
uz
z
y
l
ogi
c
t
o
i
nc
r
e
a
s
e
a
c
c
ur
a
c
y
i
n
m
a
ngo
m
a
t
ur
i
t
y
i
nde
x
c
l
a
s
s
i
f
i
c
a
t
i
on:
a
ppr
oa
c
h
f
or
de
ve
l
opi
ng
a
por
t
a
bl
e
ne
a
r
-
i
nf
r
a
r
e
d
s
pe
c
t
r
os
c
o
py
de
vi
c
e
,”
Se
ns
o
r
s
,
vol
.
22,
no.
24,
2022,
doi
:
10.3390/
s
22249704.
[
30]
E
. K
a
l
ope
s
a
,
K
. K
a
r
yot
i
s
,
N
. T
z
i
ol
a
s
,
N
. T
s
a
ki
r
i
di
s
, N
. S
a
m
a
r
i
na
s
, a
nd
G
. Z
a
l
i
d
i
s
, “
E
s
t
i
m
a
t
i
on of
s
uga
r
c
ont
e
nt
i
n w
i
ne
gr
a
pe
s
vi
a
I
n
S
i
t
u
V
N
I
R
–
S
W
I
R
po
i
nt
s
pe
c
t
r
os
c
opy
us
i
ng
e
xpl
a
i
na
bl
e
a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
n
c
e
t
e
c
hni
que
s
,”
Se
n
s
or
s
,
vol
.
23,
no.
3,
2023,
doi
:
10.3390/
s
23031065.
[
31]
M
.
S
hi
ba
ng,
“
N
onde
s
t
r
uc
t
i
ve
de
t
e
r
m
i
na
t
i
on
of
ki
w
i
f
r
ui
t
S
S
C
us
i
ng
vi
s
i
bl
e
/
n
e
a
r
-
i
nf
r
a
r
e
d
s
pe
c
t
r
os
c
opy
w
i
t
h
ge
ne
t
i
c
a
l
gor
i
t
hm
,”
J
our
nal
of
E
ngi
ne
e
r
i
ng Sc
i
e
nc
e
and T
e
c
hnol
ogy
R
e
v
i
e
w
, vol
. 14, no. 1, pp. 100
–
106, 2021, doi
:
10.25103/
j
e
s
t
r
.141.11.
[
32]
S
.
X
u,
H
.
L
u,
C
.
F
e
r
e
nc
e
,
a
nd
Q
.
Z
ha
ng,
“
V
i
s
i
bl
e
/
ne
a
r
i
nf
r
a
r
e
d
r
e
f
l
e
c
t
i
on
s
pe
c
t
r
om
e
t
e
r
a
nd
e
l
e
c
t
r
oni
c
nos
e
da
t
a
f
us
i
on
a
s
a
n
a
c
c
ur
a
c
y i
m
pr
ove
m
e
nt
m
e
t
hod f
or
por
t
a
bl
e
t
ot
a
l
s
ol
ubl
e
s
ol
i
d c
ont
e
nt
d
e
t
e
c
t
i
on
of
or
a
nge
,”
A
ppl
i
e
d Sc
i
e
nc
e
s
, vol
. 9, no. 18,
2019,
doi
:
10.3390/
a
pp9183761.
[
33]
X
.
Y
a
ng
e
t
al
.
,
“
D
e
t
e
r
m
i
na
t
i
on
of
t
he
s
ol
ubl
e
s
ol
i
ds
c
ont
e
nt
i
n
K
or
l
a
f
r
a
gr
a
nt
pe
a
r
s
ba
s
e
d
on
vi
s
i
bl
e
a
nd
ne
a
r
-
i
nf
r
a
r
e
d
s
pe
c
t
r
os
c
opy
c
om
bi
ne
d
w
i
t
h
m
ode
l
a
na
l
ys
i
s
a
nd
va
r
i
a
bl
e
s
e
l
e
c
t
i
on,”
F
r
ont
i
e
r
s
i
n
P
l
ant
Sc
i
e
nc
e
,
vol
.
13,
2022,
doi
:
10.3389/
f
pl
s
.2022.938162.
[
34]
Z
.
C
a
i
,
S
.
J
i
a
ng,
J
.
D
ong,
a
nd
S
.
T
a
ng,
“
A
n
a
r
t
i
f
i
c
i
a
l
pl
a
nt
c
om
m
un
i
t
y
a
l
g
or
i
t
hm
f
or
t
he
a
c
c
ur
a
t
e
r
a
nge
-
f
r
e
e
pos
i
t
i
oni
ng
of
w
i
r
e
l
e
s
s
s
e
ns
or
ne
t
w
or
ks
,”
Se
n
s
or
s
, vol
. 23, no. 5, 2023, doi
:
10.3390/
s
230528
04.
[
35]
A
.
Z
e
b
e
t
al
.
,
“
T
ow
a
r
ds
s
w
e
e
t
ne
s
s
c
l
a
s
s
i
f
i
c
a
t
i
on
of
or
a
nge
c
ul
t
i
va
r
s
us
i
ng
s
hor
t
-
w
a
ve
N
I
R
s
pe
c
t
r
os
c
opy,”
S
c
i
e
nt
i
f
i
c
R
e
por
t
s
,
vol
.
13, no. 1, 2023, doi
:
10.1038/
s
41598
-
022
-
27297
-
2.
[
36]
R
.
P
our
da
r
ba
ni
,
S
.
S
a
bz
i
,
M
.
H
.
R
ohba
n,
G
.
G
.
-
M
a
t
e
os
,
J
.
P
a
l
i
w
a
l
,
a
nd
J
.
M
.
M
.
-
M
a
r
t
í
ne
z
,
“
U
s
i
ng
m
e
t
a
he
ur
i
s
t
i
c
a
l
gor
i
t
hm
s
t
o
i
m
pr
ove
t
he
e
s
t
i
m
a
t
i
on
of
a
c
i
di
t
y
i
n
F
uj
i
a
ppl
e
s
us
i
ng
N
I
R
s
pe
c
t
r
os
c
opy,”
A
i
n
Sham
s
E
ngi
ne
e
r
i
ng
J
our
nal
,
vol
.
13,
no.
6,
2022,
doi
:
10.1016/
j
.a
s
e
j
.2022.101776.
[
37]
A
.
P
ut
t
i
pi
pa
t
ka
j
or
n,
A
.
T
e
r
dw
ongw
or
a
kul
,
A
.
P
ut
t
i
pi
pa
t
ka
j
or
n,
S
.
K
ul
m
ut
i
w
a
t
,
P
.
S
a
ngw
a
na
ngkul
,
a
nd
T
.
C
he
e
ps
om
s
ong,
“
I
ndi
r
e
c
t
pr
e
di
c
t
i
on
of
d
r
y
m
a
t
t
e
r
i
n
du
r
i
a
n
pul
p
w
i
t
h
c
om
bi
ne
d
f
e
a
t
ur
e
s
us
i
ng
m
i
ni
a
t
ur
e
N
I
R
s
pe
c
t
r
ophot
om
e
t
e
r
,”
I
E
E
E
A
c
c
e
s
s
,
vol
. 11, pp. 84810
–
84821, 2023, doi
:
10.1109/
A
C
C
E
S
S
.2023.3303020.
[
38]
P
.
M
i
s
hr
a
a
nd
E
.
W
ol
t
e
r
i
ng,
“
S
e
m
i
-
s
upe
r
vi
s
e
d
r
obus
t
m
ode
l
s
f
or
pr
e
di
c
t
i
ng
dr
y
m
a
t
t
e
r
i
n
m
a
ngo
f
r
ui
t
w
i
t
h
ne
a
r
-
i
nf
r
a
r
e
d
s
pe
c
t
r
os
c
opy,”
P
os
t
ha
r
v
e
s
t
B
i
ol
ogy
and T
e
c
hnol
ogy
, vol
. 200, 2023, doi
:
10.10
16/
j
.pos
t
ha
r
vbi
o.2023.112335.
[
39]
P
.
E
s
c
á
r
a
t
e
,
G
.
F
a
r
i
a
s
,
P
.
N
a
r
a
nj
o,
a
nd
J
.
P
.
Z
of
f
ol
i
,
“
E
s
t
i
m
a
t
i
on
of
s
ol
ubl
e
s
ol
i
ds
f
or
s
t
one
f
r
ui
t
va
r
i
e
t
i
e
s
ba
s
e
d
on
ne
a
r
-
i
nf
r
a
r
e
d
s
pe
c
t
r
a
us
i
ng m
a
c
hi
ne
l
e
a
r
ni
ng t
e
c
hni
que
s
,”
Se
n
s
or
s
, vol
. 22, no. 16, 2022, doi
:
10.3390/
s
22166081.
[
40]
J
.
A
.
M
a
r
t
i
ns
,
D
.
R
odr
i
gue
s
,
A
.
M
.
C
a
va
c
o,
M
.
D
.
A
nt
une
s
,
a
nd
R
.
G
ue
r
r
a
,
“
E
s
t
i
m
a
t
i
on
of
s
ol
ubl
e
s
ol
i
ds
c
ont
e
nt
a
nd
f
r
u
i
t
t
e
m
pe
r
a
t
ur
e
i
n
‘
R
oc
ha
’
pe
a
r
us
i
ng
V
i
s
-
N
I
R
s
pe
c
t
r
os
c
opy
a
nd
t
he
S
pe
c
t
r
a
N
e
t
–
3
2
de
e
p
l
e
a
r
ni
ng
a
r
c
hi
t
e
c
t
ur
e
,”
P
os
t
har
v
e
s
t
B
i
ol
ogy
and T
e
c
hnol
ogy
, vol
. 199, 2023, doi
:
10.1016/
j
.pos
t
ha
r
vbi
o.2023.112281.
[
41]
Y
.
H
a
o,
X
.
L
i
,
C
.
Z
ha
ng,
a
nd
Z
.
L
e
i
,
“
R
e
s
e
a
r
c
h
on
c
ons
t
r
uc
t
i
on
m
e
t
hod
a
nd
va
l
i
di
t
y
m
e
c
ha
ni
s
m
of
r
obus
t
a
na
l
ys
i
s
m
ode
l
i
n
s
now
pe
a
c
h
qua
l
i
t
y
de
t
e
c
t
i
on
ba
s
e
d
on
vi
s
i
bl
e
-
ne
a
r
i
nf
r
a
r
e
d
s
pe
c
t
r
os
c
opy,”
F
r
ont
i
e
r
s
i
n
N
ut
r
i
t
i
on
,
vol
.
9,
2022,
doi
:
10.3389/
f
nut
.2022.1042868.
[
42]
H
. G
a
l
a
l
, S
.
E
l
s
a
ye
d,
A
. A
l
l
a
m
,
a
nd
M
. F
a
r
ouk,
“
I
ndi
r
e
c
t
qua
nt
i
t
a
t
i
ve
a
n
a
l
ys
i
s
of
bi
oc
he
m
i
c
a
l
pa
r
a
m
e
t
e
r
s
i
n ba
n
a
na
u
s
i
ng
s
pe
c
t
r
a
l
r
e
f
l
e
c
t
a
nc
e
i
ndi
c
e
s
c
om
bi
ne
d
w
i
t
h
m
a
c
hi
ne
l
e
a
r
ni
ng
m
ode
l
i
ng,”
H
or
t
i
c
ul
t
ur
ae
,
vol
.
8,
no.
5,
2022,
doi
:
10.3390/
hor
t
i
c
ul
t
ur
a
e
8050438.
[
43]
S
.
S
.
R
.
M
.
L
a
z
i
m
,
M
.
N
.
N
a
w
i
,
S
.
K
.
B
e
j
o,
A
.
R
.
M
.
S
ha
r
i
f
f
,
a
nd
N
.
A
bdul
l
a
h,
“
P
r
e
di
c
t
i
on
a
nd
c
l
a
s
s
i
f
i
c
a
t
i
on
of
s
ol
ubl
e
s
ol
i
d
c
ont
e
nt
s
t
o
de
t
e
r
m
i
ne
t
he
m
a
t
ur
i
t
y
l
e
ve
l
of
w
a
t
e
r
m
e
l
on
us
i
ng
vi
s
i
bl
e
a
nd
s
hor
t
w
a
ve
ne
a
r
i
nf
r
a
r
e
d
s
pe
c
t
r
os
c
opy,”
I
nt
e
r
nat
i
onal
F
ood R
e
s
e
ar
c
h J
our
nal
, vol
. 29, no. 6, pp. 1372
–
1379, 2022, doi
:
10.47836/
i
f
r
j
.29.6.13.
[
44]
F
.
P
.
L
a
m
pt
e
y,
E
.
T
e
ye
,
E
.
E
.
A
ba
no,
a
nd
C
.
L
.
Y
.
A
m
ua
h,
“
A
ppl
i
c
a
t
i
on
of
ha
ndhe
l
d
N
I
R
s
pe
c
t
r
om
e
t
e
r
f
or
s
i
m
ul
t
a
ne
ous
i
de
nt
i
f
i
c
a
t
i
on
a
nd
qua
nt
i
f
i
c
a
t
i
on
of
qua
l
i
t
y
pa
r
a
m
e
t
e
r
s
i
n
i
nt
a
c
t
m
a
ngo
f
r
ui
t
s
,”
Sm
ar
t
A
gr
i
c
ul
t
ur
al
T
e
c
hnol
ogy
,
vol
.
6,
2023,
doi
:
10.1016/
j
.a
t
e
c
h.2023.100357.
[
45]
M
. M
a
nc
i
ni
e
t
al
.
, “
P
r
e
di
c
t
i
on of
s
ol
ubl
e
s
ol
i
ds
c
ont
e
nt
by m
e
a
ns
of
N
I
R
s
pe
c
t
r
os
c
opy a
nd
r
e
l
a
t
i
on w
i
t
h bot
r
yt
i
s
c
i
ne
r
e
a
t
ol
e
r
a
nc
e
i
n s
t
r
a
w
be
r
r
y c
ul
t
i
va
r
s
,”
H
or
t
i
c
ul
t
ur
ae
, vol
. 9, no. 1, 2023, doi
:
10.3390/
hor
t
i
c
ul
t
ur
a
e
9010091.
[
46]
X
.
J
i
a
ng,
M
.
Z
hu,
J
.
Y
a
o,
Y
.
Z
ha
ng,
a
nd
Y
.
L
i
u,
“
S
t
udy
on
t
he
e
f
f
e
c
t
of
a
pp
l
e
s
i
z
e
di
f
f
e
r
e
nc
e
on
s
ol
ubl
e
s
ol
i
ds
c
ont
e
nt
m
ode
l
ba
s
e
d on ne
a
r
-
i
nf
r
a
r
e
d (
N
I
R
)
s
pe
c
t
r
os
c
opy,”
J
our
nal
of
Spe
c
t
r
os
c
op
y
, vol
. 2022, 2022, doi
:
10.1155/
2022/
3740527.
[
47]
X
.
S
un,
D
.
D
e
ng,
J
.
L
i
u,
a
nd
S
.
F
e
ng,
“
M
ode
l
de
ve
l
opm
e
nt
a
nd
upda
t
e
of
por
t
a
bl
e
N
I
R
S
i
ns
t
r
um
e
nt
f
or
a
s
s
e
s
s
m
e
nt
of
i
nt
e
r
na
l
qua
l
i
t
y a
t
t
r
i
but
e
s
of
t
w
o na
ve
l
or
a
nge
va
r
i
e
t
i
e
s
,”
F
r
ont
i
e
r
s
i
n
N
ut
r
i
t
i
on
, vol
. 9,
2022, doi
:
10.3389/
f
nut
.2022.976178.
[
48]
P
.
M
i
s
hr
a
,
E
.
W
ol
t
e
r
i
ng,
B
.
B
r
ouw
e
r
,
a
nd
E
.
H
oge
ve
e
n
-
va
n
E
c
ht
e
l
t
,
“
I
m
p
r
ovi
n
g
m
oi
s
t
ur
e
a
nd
s
ol
ubl
e
s
ol
i
ds
c
ont
e
nt
pr
e
di
c
t
i
on
i
n
pe
a
r
f
r
ui
t
us
i
ng
ne
a
r
-
i
nf
r
a
r
e
d
s
pe
c
t
r
os
c
opy
w
i
t
h
va
r
i
a
bl
e
s
e
l
e
c
t
i
on
a
nd
m
o
de
l
upda
t
i
ng
a
ppr
oa
c
h,”
P
os
t
har
v
e
s
t
B
i
ol
ogy
and
Evaluation Warning : The document was created with Spire.PDF for Python.